Machine learning in earth sciences

Last updated

Applications of machine learning (ML) in earth sciences include geological mapping, gas leakage detection and geological feature identification. Machine learning is a subdiscipline of artificial intelligence aimed at developing programs that are able to classify, cluster, identify, and analyze vast and complex data sets without the need for explicit programming to do so. [1] Earth science is the study of the origin, evolution, and future [2] of the Earth. The earth's system can be subdivided into four major components including the solid earth, atmosphere, hydrosphere, and biosphere. [3]

Contents

A variety of algorithms may be applied depending on the nature of the task. Some algorithms may perform significantly better than others for particular objectives. For example, convolutional neural networks (CNNs) are good at interpreting images, whilst more general neural networks may be used for soil classification, [4] but can be more computationally expensive to train than alternatives such as support vector machines. The range of tasks to which ML (including deep learning) is applied has been ever-growing in recent decades, as has the development of other technologies such as unmanned aerial vehicles (UAVs), [5] ultra-high resolution remote sensing technology, and high-performance computing. [6] This has led to the availability of large high-quality datasets and more advanced algorithms.

Significance

Complexity of earth science

Problems in earth science are often complex. [7] It is difficult to apply well-known and described mathematical models to the natural environment, therefore machine learning is commonly a better alternative for such non-linear problems. [8] Ecological data are commonly non-linear and consist of higher-order interactions, and together with missing data, traditional statistics may underperform as unrealistic assumptions such as linearity are applied to the model. [9] [10] A number of researchers found that machine learning outperforms traditional statistical models in earth science, such as in characterizing forest canopy structure, [11] predicting climate-induced range shifts, [12] and delineating geologic facies. [13] Characterizing forest canopy structure enables scientists to study vegetation response to climate change. [14] Predicting climate-induced range shifts enable policy makers to adopt suitable conversation method to overcome the consequences of climate change. [15] Delineating geologic facies helps geologists to understand the geology of an area, which is essential for the development and management of an area. [16]

Inaccessible data

In Earth Sciences, some data are often difficult to access or collect, therefore inferring data from data that are easily available by machine learning method is desirable. [10] For example, geological mapping in tropical rainforests is challenging because the thick vegetation cover and rock outcrops are poorly exposed. [17] Applying remote sensing with machine learning approaches provides an alternative way for rapid mapping without the need of manually mapping in the unreachable areas. [17]

Reduce time costs

Machine learning can also reduce the efforts done by experts, as manual tasks of classification and annotation etc are the bottlenecks in the workflow of the research of earth science. [10] Geological mapping, especially in a vast, remote area is labour, cost and time-intensive with traditional methods. [18] Incorporation of remote sensing and machine learning approaches can provide an alternative solution to eliminate some field mapping needs. [18]

Consistent and bias-free

Consistency and bias-free is also an advantage of machine learning compared to manual works by humans. In research comparing the performance of human and machine learning in the identification of dinoflagellates, machine learning is found to be not as prone to systematic bias as humans. [19] A recency effect that is present in humans is that the classification often biases towards the most recently recalled classes. [19] In a labelling task of the research, if one kind of dinoflagellates occurs rarely in the samples, then expert ecologists commonly will not classify it correctly. [19] The systematic bias strongly deteriorate the classification accuracies of humans. [19]

Optimal machine learning algorithm

The extensive usage of machine learning in various fields has led to a wide range of algorithms of learning methods being applied. Choosing the optimal algorithm for a specific purpose can lead to a significant boost in accuracy: [20] for example, the lithological mapping of gold-bearing granite-greenstone rocks in Hutti, India with AVIRIS-NG hyperspectral data, shows more than 10% difference in overall accuracy between using support vector machines (SVMs) and random forest. [21]

Some algorithms can also reveal hidden important information: white box models are transparent models, the outputs of which can be easily explained, while black box models are the opposite. [20] For example, although an SVM yielded the best result in landslide susceptibility assessment accuracy, the result cannot be rewritten in the form of expert rules that explain how and why an area was classified as that specific class. [7] In contrast, decision trees are transparent and easily understood, and the user can observe and fix the bias if any is present in such models. [7]

If computational resource is a concern, more computationally demanding learning methods such as deep neural networks are less preferred, despite the fact that they may outperform other algorithms, such as in soil classification. [4]

Usage

Mapping

Geological or lithological mapping and mineral prospectivity mapping

Geological or lithological mapping produces maps showing geological features and geological units. Mineral prospectivity mapping utilizes a variety of datasets such as geological maps and aeromagnetic imagery to produce maps that are specialized for mineral exploration. [22] Geological, lithological, and mineral prospectivity mapping can be carried out by processing data with ML techniques, with the input of spectral imagery obtained from remote sensing and geophysical data. [23] Spectral imaging is also used – the imaging of wavelength bands in the electromagnetic spectrum, while conventional imaging captures three wavelength bands (red, green, blue) in the electromagnetic spectrum. [24]

Random forests and SVMs are some algorithms commonly used with remotely-sensed geophysical data, while Simple Linear Iterative Clustering-Convolutional Neural Network (SLIC-CNN) [5] and Convolutional Neural Networks (CNNs) [18] are commonly applied to aerial imagery. Large scale mapping can be carried out with geophysical data from airborne and satellite remote sensing geophysical data, [21] and smaller-scale mapping can be carried out with images from Unmanned Aerial Vehicles (UAVs) for higher resolution. [5]

Vegetation cover is one of the major obstacles for geological mapping with remote sensing, as reported in various research, both in large-scale and small-scale mapping. Vegetation affects the quality of spectral images, [23] or obscures the rock information in aerial images. [5]

Example applications in Geological, Lithological, and Mineral Prospectivity Mapping
ObjectiveInput datasetLocationMachine Learning Algorithms (MLAs)Performance
Lithological Mapping of Gold-bearing granite-greenstone rocks [21] AVIRIS-NG hyperspectral dataHutti, India Linear Discriminant Analysis (LDA),

Random Forest,

Support Vector Machine (SVM)

Support Vector Machine (SVM) outperforms the other Machine Learning Algorithms (MLAs)
Lithological Mapping in the Tropical Rainforest [17] Magnetic Vector Inversion, Ternary RGB map, Shuttle Radar Topography Mission (SRTM), false color (RGB) of Landsat 8 combining bands 4, 3 and 2Cinzento Lineament, BrazilRandom ForestTwo predictive maps were generated:

(1) Map generated with remote sensing data only has a 52.7% accuracy when compared to the geological map, but several new possible lithological units are identified

(2) Map generated with remote sensing data and spatial constraints has a 78.7% accuracy but no new possible lithological units are identified

Geological Mapping for mineral exploration [25] Airborne polarimetric Terrain Observation with Progressive Scans SAR (TopSAR),

geophysical data

Western TasmaniaRandom ForestLow reliability of TopSAR for geological mapping, but accurate with geophysical data.
Geological and Mineralogical mapping[ citation needed ]Multispectral and hyperspectral satellite dataCentral Jebilet,

Morocco

Support Vector Machine (SVM)The accuracy of using hyperspectral data for classifying is slightly higher than that using multispectral data, obtaining 93.05% and 89.24% respectively, showing that machine learning is a reliable tool for mineral exploration.
Integrating Multigeophysical Data into a Cluster Map [26] Airborne magnetic,

frequency electromagnetic, radiometric measurements, ground gravity measurements

Trøndelag, Mid-NorwayRandom ForestThe cluster map produced has a satisfactory relationship with the existing geological map but with minor misfits.
High-Resolution Geological Mapping with Unmanned Aerial Vehicle (UAV) [5] Ultra-resolution RGB imagesTaili waterfront,

Liaoning Province, China

Simple Linear Iterative Clustering-Convolutional Neural Network (SLIC-CNN)The result is satisfactory in mapping major geological units but showed poor performance in mapping pegmatites, fine-grained rocks and dykes. UAVs were unable to collect rock information where the rocks were not exposed.
Surficial Geology Mapping [18]

Remote Predictive Mapping (RPM)

 Aerial Photos,

Landsat Reflectance, High-Resolution Digital Elevation Data

South Rae Geological Region,

Northwest Territories, Canada

Convolutional Neural Networks (CNN),

Random Forest

The resulting accuracy of CNN was 76% in the locally trained area, while 68% for an independent test area. The CNN achieved a slightly higher accuracy of 4% than the Random Forest.
Methods of Splitting of the Datasets into Training Dataset and Testing Dataset As the training of machine learning for landslide susceptibility mapping requires both training and testing datasets, splitting the dataset is required. Two splitting methods for the datasets are presented on the geologic map of the east Cumberland Gap. The method presented on the left, 'Splitting into two adjacent areas', is more useful as the automation algorithm can carry out mapping of a new area with the input of expert processed data of adjacent land. The cyan pixels show the training dataset while the remaining show the testing. Landslide susceptibility mapping dataset splitting.png
Methods of Splitting of the Datasets into Training Dataset and Testing Dataset
As the training of machine learning for landslide susceptibility mapping requires both training and testing datasets, splitting the dataset is required. Two splitting methods for the datasets are presented on the geologic map of the east Cumberland Gap. The method presented on the left, 'Splitting into two adjacent areas', is more useful as the automation algorithm can carry out mapping of a new area with the input of expert processed data of adjacent land. The cyan pixels show the training dataset while the remaining show the testing.

Landslide susceptibility and hazard mapping

Landslide susceptibility refers to the probability of landslide of a certain geographical location, which is dependent on local terrain conditions. [27] Landslide susceptibility mapping can highlight areas prone to landslide risks, which is useful for urban planning and disaster management. [7] Such datasets for ML algorithms usually include topographic information, lithological information, satellite images, etc., and some may include land use, land cover, drainage information, and vegetation cover [7] [28] [29] [30] according to the study requirements. As usual, for training an ML model for landslide susceptibility mapping, training and testing datasets are required. [7] There are two methods of allocating datasets for training and testing: one is to randomly split the study area for the datasets; another is to split the whole study into two adjacent parts for the two datasets. To test classification models, the common practice is to split the study area randomly; [7] [31] however, it is more useful if the study area can be split into two adjacent parts so that an automation algorithm can carry out mapping of a new area with the input of expert-processed data of adjacent land. [7]

Example applications in Landslide Susceptibility and Hazard Mapping
ObjectiveInput datasetLocationMachine Learning Algorithms (MLAs)Performance
Landslide Susceptibility Assessment [7] Digital Elevation Model (DEM), Geological Map, 30m Landsat ImageryFruška Gora Mountain, SerbiaSupport Vector Machine (SVM),

Decision Trees, Logistic Regression

Support Vector Machine (SVM) outperforms others
Landslide Susceptibility Mapping [31] ASTER satellite-based geomorphic data, geological mapsHonshu Island, Japan Artificial Neural Network (ANN) Accuracy greater than 90% for determining the probability of landslide.
Landslide Susceptibility Zonation through ratings [28] Spatial data layers with slope, aspect, relative relief, lithology, structural features, land use, land cover, drainage densityParts of Chamoli and Rudraprayag districts of the State of Uttarakhand, IndiaArtificial Neural Network (ANN)The AUC of this approach reaches 0.88. This approach generated an accurate assessment of landslide risks.
Regional Landslide Hazard Analysis [29] Topographic slope, aspect, and curvature; distance from drainage, lithology, distance from lineament, land cover from TM satellite images, vegetation index (NDVI), precipitation dataEastern Selangor state, MalaysiaArtificial Neural Network (ANN)The approach achieved 82.92% accuracy of prediction.

Feature identification and detection

Data Augmentation Technique In the preparation of the dataset for rock fracture recognition, data augmentation was performed. This technique is commonly used for increasing the training dataset size and variability. Although the randomly-cropped samples and the flipped samples come from the same image, the processed samples are unique. This technique can prevent the problem of data scarcity and overfitting the model. Data Augmentation of rock images revised.jpg
Data Augmentation Technique
In the preparation of the dataset for rock fracture recognition, data augmentation was performed. This technique is commonly used for increasing the training dataset size and variability. Although the randomly-cropped samples and the flipped samples come from the same image, the processed samples are unique. This technique can prevent the problem of data scarcity and overfitting the model.

Discontinuity analyses

Discontinuities such as fault planes and bedding planes have important implications in civil engineering. [32] Rock fractures can be recognized automatically by machine learning through photogrammetric analysis, even with the presence of interfering objects such as vegetation. [33] In ML training for classifying images, data augmentation is a common practice to avoid overfitting and increase the training dataset size and variability. [33] For example, in a study of rock fracture recognition, 68 images for training and 23 images for testing were prepared via random splitting. [33] Data augmentation was performed, increasing the training dataset size to 8704 images by flipping and random cropping. [33] The approach was able to recognize rock fractures accurately in most cases. [33] Both the negative prediction value (NPV) and the specificity were over 0.99. [33] This demonstrated the robustness of discontinuity analyses with machine learning.

Example applications in Discontinuity Analysis
ObjectiveInput datasetLocationMachine Learning Algorithms (MLAs)Performance
Recognition of Rock Fractures [33] Rock images collected in field surveyGwanak Mountain and Bukhan Mountain,

Seoul, Korea and Jeongseon-gun, Gangwon-do, Korea

Convolutional Neural Network (CNN)The approach was able to recognize the rock fractures accurately in most cases. The NPV and the specificity were over 0.99.

Carbon dioxide leakage detection

Quantifying carbon dioxide leakage from a geological sequestration site has gained increased attention as the public is interested in whether carbon dioxide is stored underground safely and effectively. [34] Carbon dioxide leakage from a geological sequestration site can be detected indirectly with the aid of remote sensing and an unsupervised clustering algorithm such as Iterative Self-Organizing Data Analysis Technique (ISODATA). [35] The increase in soil CO2 concentration causes a stress response for plants by inhibiting plant respiration, as oxygen is displaced by carbon dioxide. [36] The vegetation stress signal can be detected with the Normalized Difference Red Edge Index (NDRE). [36] The hyperspectral images are processed by the unsupervised algorithm, clustering pixels with similar plant responses. [36] The hyperspectral information in areas with known CO2 leakage is extracted so that areas with leakage can be matched with the clustered pixels with spectral anomalies. [36] Although the approach can identify CO2 leakage efficiently, there are some limitations that require further study. [36] The NDRE may not be accurate due to reasons like higher chlorophyll absorption, variation in vegetation, and shadowing effects; therefore, some stressed pixels can be incorrectly classed as healthy. [36] Seasonality, groundwater table height may also affect the stress response to CO2 of the vegetation. [36]

Example applications in Carbon Dioxide Leakage Detection
ObjectiveInput datasetLocationMachine Learning Algorithms (MLAs)Performance
Detection of CO2 leak from a geologic sequestration site [35] Aerial hyperspectral imageryThe Zero Emissions Research and Technology (ZERT), USIterative Self-Organizing Data Analysis Technique (ISODATA) methodThe approach was able to detect areas with CO2 leaks however other factors like the growing seasons of the vegetation also interfere with the results.

Quantification of water inflow

The rock mass rating (RMR) [37] system is a widely adopted rock mass classification system by geomechanical means with the input of six parameters. The amount of water inflow is one of the inputs of the classification scheme, representing the groundwater condition. Quantification of the water inflow in the faces of a rock tunnel was traditionally carried out by visual observation in the field, which is labour and time consuming, and fraught with safety concerns. [38] Machine learning can determine water inflow by analyzing images taken on the construction site. [38] The classification of the approach mostly follows the RMR system, but combining damp and wet states, as it is difficult to distinguish only by visual inspection. [38] [37] The images were classified into the non-damaged state, wet state, dripping state, flowing state, and gushing state. [38] The accuracy of classifying the images was approximately 90%. [38]

Example applications in Quantification of Water Inflow
ObjectiveInput datasetLocationMachine Learning Algorithms (MLAs)Performance
Quantification of water inflow in rock tunnel faces [38] Images of water inflow-Convolutional Neural Network (CNN)The approach achieved a mean accuracy of 93.01%.

Classification

Soil classification

The most popular cost-effective method od soil investigation method is cone penetration testing (CPT). [39] The test is carried out by pushing a metallic cone through the soil: the force required to push at a constant rate is recorded as a quasi-continuous log. [4] Machine learning can classify soil with the input of CPT data. [4] In an attempt to classify with ML, there are two tasks required to analyze the data, namely segmentation and classification. [4] Segmentation can be carried out with the Constraint Clustering and Classification (CONCC) algorithm to split a single series data into segments. [4] Classification can then be carried out by algorithms such as decision trees, SVMs, or neural networks. [4]

Example applications in Soil Classification
ObjectiveInput datasetLocationMachine Learning Algorithms (MLAs)Performance
Soil classification [4] Cone Penetration Test (CPT) logs-Decision Trees, Artificial Neural Network (ANN), Support Vector MachineThe Artificial Neural Network (ANN) outperformed the others in classifying humus clay and peat, while decision trees outperformed the others in classifying clayey peat. SVMs gave the poorest performance among the three.

Geological structure classification

Effect of Colour Image and Greyscale Image The figure shows an image of a fold. The left image shows a colour image, while the one in the right shows a grayscale image. The difference in the accuracy of classifying the geological structure between colour images and grayscale images is little. Geological feature recognition.png
Effect of Colour Image and Greyscale Image
The figure shows an image of a fold. The left image shows a colour image, while the one in the right shows a grayscale image. The difference in the accuracy of classifying the geological structure between colour images and grayscale images is little.

Exposed geological structures such as anticlines, ripple marks, and xenoliths can be identified automatically with deep learning models. [40] Research has demonstrated that three-layer CNNs and transfer learning have strong accuracy (about 80% and 90% respectively), while others like k-nearest neighbors (k-NN), regular neural nets, and extreme gradient boosting (XGBoost) have low accuracies (ranging from 10% - 30%). [40] The grayscale images and colour images were both tested, with the accuracy difference being little, implying that colour is not very important in identifying geological structures. [40]

Example applications in Geological Structure Classification
ObjectiveInput datasetLocationMachine Learning Algorithms (MLAs)Performance
Geological structures classification [40] Images of geological structures-k-nearest neighbors (k-NN), Artificial Neural Network (ANN), Extreme Gradient Boosting (XGBoost), three-layer Convolutional Neural Network (CNN), transfer learningThree-layer Convolutional Neural Network (CNN) and Transfer Learning reached accuracies of about 80% and 90% respectively, while others were low (10% to 30%).

Forecast and predictions

Earthquake early warning systems and forecasting

Earthquake warning systems are often vulnerable to local impulsive noise, therefore giving out false alerts. [41] False alerts can be eliminated by discriminating the earthquake waveforms from noise signals with the aid of ML methods. The method consists of two parts, the first being unsupervised learning with a generative adversarial network (GAN) to learn and extract features of first-arrival P-waves, and the second being use of a random forest to discriminate P-waves. This approach achieved 99.2% in recognizing P-waves, and can avoid false triggers by noise signals with 98.4% accuracy. [41]

Earthquakes can be produced in a laboratory settings to mimic real-world ones. With the help of machine learning, the patterns of acoustic signals as precursors for earthquakes can be identified. Predicting the time remaining before failure was demonstrated in a study with continuous acoustic time series data recorded from a fault. The algorithm applied was a random forest, trained with a set of slip events, performing strongly in predicting the time to failure. It identified acoustic signals to predict failures, with one of them being previously unidentified. Although this laboratory earthquake is not as complex as a natural one, progress was made that guides future earthquake prediction work. [42]

Example applications in Earthquake Prediction
ObjectiveInput datasetLocationMachine Learning Algorithms (MLAs)Performance
Discriminating earthquake waveforms [41] Earthquake datasetSouthern California and JapanGenerative adversarial network (GAN), random forestThis approach can recognise P waves with 99.2% accuracy and avoid false triggers by noise signals with 98.4% accuracy.
Predicting time remaining for next earthquake [42] Continuous acoustic time series data-Random ForestThe R2 value of the prediction reached 0.89, which demonstrated excellent performance.

Streamflow discharge prediction

Real-time streamflow data is integral for decision making (e.g., evacuations, or regulation of reservoir water levels during flooding). [43] Streamflow data can be estimated by data provided by stream gauges, which measure the water level of a river. However, water and debris from flooding may damage stream gauges, resulting in lack of essential real-time data. The ability of machine learning to infer missing data [10] enables it to predict streamflow with both historical stream gauge data and real-time data. Streamflow Hydrology Estimate using Machine Learning (SHEM) is a model that can serve this purpose. To verify its accuracies, the prediction result was compared with the actual recorded data, and the accuracies were found to be between 0.78 to 0.99.

Example applications in Streamflow Discharge Prediction
ObjectiveInput datasetLocationMachine Learning Algorithms (MLAs)Performance
Streamflow Estimate with data missing [44] Streamgage data from NWIS-WebFour diverse watersheds in Idaho, US and Washington, USRandom ForestsThe estimates correlated well to the historical data of the discharges. The accuracy ranges from 0.78 to 0.99.

Challenge

Inadequate training data

An adequate amount of training and validation data is required for machine learning. [10] However, some very useful products like satellite remote sensing data only have decades of data since the 1970s. If one is interested in the yearly data, then only less than 50 samples are available. [45] Such amount of data may not be adequate. In a study of automatic classification of geological structures, the weakness of the model is the small training dataset, even though with the help of data augmentation to increase the size of the dataset. [40] Another study of predicting streamflow found that the accuracies depend on the availability of sufficient historical data, therefore sufficient training data determine the performance of machine learning. [44] Inadequate training data may lead to a problem called overfitting. Overfitting causes inaccuracies in machine learning [46] as the model learns about the noise and undesired details.

Limited by data input

Machine learning cannot carry out some of the tasks as a human does easily. For example, in the quantification of water inflow in rock tunnel faces by images for Rock Mass Rating system (RMR), [38] the damp and the wet state was not classified by machine learning because discriminating the two only by visual inspection is not possible. In some tasks, machine learning may not able to fully substitute manual work by a human.

Black-box operation

Black-box Operation of some Machine Learning Algorithms In a black-box operation, a user only know about the input and output but not the process. Artificial Neural Network (ANN) is an example of a black-box operation. The user has no way to understand the logic of the hidden layers. Blackbox3D-withGraphs.svg
Black-box Operation of some Machine Learning Algorithms
In a black-box operation, a user only know about the input and output but not the process. Artificial Neural Network (ANN) is an example of a black-box operation. The user has no way to understand the logic of the hidden layers.

In many machine learning algorithms, for example, Artificial Neural Network (ANN), it is considered as 'black box' approach as clear relationships and descriptions of how the results are generated in the hidden layers are unknown. [47] 'White-box' approach such as decision tree can reveal the algorithm details to the users. [48] If one wants to investigate the relationships, such 'black-box' approaches are not suitable. However, the performances of 'black-box' algorithms are usually better. [49]

Related Research Articles

<span class="mw-page-title-main">Neural network (machine learning)</span> Computational model used in machine learning, based on connected, hierarchical functions

In machine learning, a neural network is a model inspired by the structure and function of biological neural networks in animal brains.

<span class="mw-page-title-main">Lidar</span> Method of spatial measurement using laser

Lidar is a method for determining ranges by targeting an object or a surface with a laser and measuring the time for the reflected light to return to the receiver. Lidar may operate in a fixed direction or it may scan multiple directions, in which case it is known as lidar scanning or 3D laser scanning, a special combination of 3-D scanning and laser scanning. Lidar has terrestrial, airborne, and mobile applications.

<span class="mw-page-title-main">Digital elevation model</span> 3D computer-generated imagery and measurements of terrain

A digital elevation model (DEM) or digital surface model (DSM) is a 3D computer graphics representation of elevation data to represent terrain or overlaying objects, commonly of a planet, moon, or asteroid. A "global DEM" refers to a discrete global grid. DEMs are used often in geographic information systems (GIS), and are the most common basis for digitally produced relief maps. A digital terrain model (DTM) represents specifically the ground surface while DEM and DSM may represent tree top canopy or building roofs.

<span class="mw-page-title-main">Remote sensing</span> Acquisition of information at a significant distance from the subject

Remote sensing is the acquisition of information about an object or phenomenon without making physical contact with the object, in contrast to in situ or on-site observation. The term is applied especially to acquiring information about Earth and other planets. Remote sensing is used in numerous fields, including geophysics, geography, land surveying and most Earth science disciplines. It also has military, intelligence, commercial, economic, planning, and humanitarian applications, among others.

Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks without explicit instructions. Advances in the field of deep learning have allowed neural networks to surpass many previous approaches in performance.

<span class="mw-page-title-main">Land cover</span> Physical material covering the surface of Earth

Land cover is the physical material at the land surface of Earth. Land covers include flora, concrete, built structures, bare ground, and temporary water. Earth cover is the expression used by ecologist Frederick Edward Clements that has its closest modern equivalent being vegetation. The expression continues to be used by the United States Bureau of Land Management.

In data analysis, anomaly detection is generally understood to be the identification of rare items, events or observations which deviate significantly from the majority of the data and do not conform to a well defined notion of normal behavior. Such examples may arouse suspicions of being generated by a different mechanism, or appear inconsistent with the remainder of that set of data.

<span class="mw-page-title-main">Spiking neural network</span> Artificial neural network that mimics neurons

Spiking neural networks (SNNs) are artificial neural networks (ANN) that more closely mimic natural neural networks. These models leverage timing of discrete spikes as the main information carrier.

In statistics and machine learning, ensemble methods use multiple learning algorithms to obtain better predictive performance than could be obtained from any of the constituent learning algorithms alone. Unlike a statistical ensemble in statistical mechanics, which is usually infinite, a machine learning ensemble consists of only a concrete finite set of alternative models, but typically allows for much more flexible structure to exist among those alternatives.

<span class="mw-page-title-main">Deep learning</span> Branch of machine learning

Deep learning is a subset of machine learning that focuses on utilizing neural networks to perform tasks such as classification, regression, and representation learning. The field takes inspiration from biological neuroscience and is centered around stacking artificial neurons into layers and "training" them to process data. The adjective "deep" refers to the use of multiple layers in the network. Methods used can be either supervised, semi-supervised or unsupervised.

<span class="mw-page-title-main">Feature learning</span> Set of learning techniques in machine learning

In machine learning (ML), feature learning or representation learning is a set of techniques that allow a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task.

<span class="mw-page-title-main">MNIST database</span> Database of handwritten digits

The MNIST database is a large database of handwritten digits that is commonly used for training various image processing systems. The database is also widely used for training and testing in the field of machine learning. It was created by "re-mixing" the samples from NIST's original datasets. The creators felt that since NIST's training dataset was taken from American Census Bureau employees, while the testing dataset was taken from American high school students, it was not well-suited for machine learning experiments. Furthermore, the black and white images from NIST were normalized to fit into a 28x28 pixel bounding box and anti-aliased, which introduced grayscale levels.

Data augmentation is a statistical technique which allows maximum likelihood estimation from incomplete data. Data augmentation has important applications in Bayesian analysis, and the technique is widely used in machine learning to reduce overfitting when training machine learning models, achieved by training models on several slightly-modified copies of existing data.

Machine learning in bioinformatics is the application of machine learning algorithms to bioinformatics, including genomics, proteomics, microarrays, systems biology, evolution, and text mining.

<span class="mw-page-title-main">Remote sensing in geology</span> Data acquisition method for earth sciences

Remote sensing is used in the geological sciences as a data acquisition method complementary to field observation, because it allows mapping of geological characteristics of regions without physical contact with the areas being explored. About one-fourth of the Earth's total surface area is exposed land where information is ready to be extracted from detailed earth observation via remote sensing. Remote sensing is conducted via detection of electromagnetic radiation by sensors. The radiation can be naturally sourced, or produced by machines and reflected off of the Earth surface. The electromagnetic radiation acts as an information carrier for two main variables. First, the intensities of reflectance at different wavelengths are detected, and plotted on a spectral reflectance curve. This spectral fingerprint is governed by the physio-chemical properties of the surface of the target object and therefore helps mineral identification and hence geological mapping, for example by hyperspectral imaging. Second, the two-way travel time of radiation from and back to the sensor can calculate the distance in active remote sensing systems, for example, Interferometric synthetic-aperture radar. This helps geomorphological studies of ground motion, and thus can illuminate deformations associated with landslides, earthquakes, etc.

Multi-focus image fusion is a multiple image compression technique using input images with different focus depths to make one output image that preserves all information.

Geological structure measurement by LiDAR technology is a remote sensing method applied in structural geology. It enables monitoring and characterisation of rock bodies. This method's typical use is to acquire high resolution structural and deformational data for identifying geological hazards risk, such as assessing rockfall risks or studying pre-earthquake deformation signs.

<span class="mw-page-title-main">Biswajeet Pradhan</span> Spatial scientist, modeler, and author

Biswajeet Pradhan is a spatial scientist, modeller, author and who is now working as a Distinguished Professor and the founding Director of the Centre for Advanced Modelling and Geo-spatial Information Systems (CAMGIS), Faculty of Engineering and IT at the University of Technology Sydney, Australia. He is working primarily in the fields of remote sensing, geographic information systems (GIS), complex modelling, machine learning and Artificial intelligence (AI) based algorithms and their application to natural hazards, natural resources and environmental problems. Many of his research outputs were put into practice. His research platform is mainly Asia and Australia, and he has been sharing his findings worldwide. He is also a permanent resident of Australia and Malaysia.

Land cover maps are tools that provide vital information about the Earth's land use and cover patterns. They aid policy development, urban planning, and forest and agricultural monitoring.

The Fashion MNIST dataset is a large freely available database of fashion images that is commonly used for training and testing various machine learning systems. Fashion-MNIST was intended to serve as a replacement for the original MNIST database for benchmarking machine learning algorithms, as it shares the same image size, data format and the structure of training and testing splits.

References

  1. ↑ Mueller, J. P., & Massaron, L. (2021). Machine learning for dummies. John Wiley & Sons.
  2. ↑ Resources., National Academies Press (U.S.) National Research Council (U.S.). Commission on Geosciences, Environment, and (2001). Basic research opportunities in earth science. National Academies Press. OCLC   439353646.{{cite book}}: CS1 maint: multiple names: authors list (link)
  3. ↑ Miall, A.D. (December 1995). "The blue planet: An introduction to earth system science". Earth-Science Reviews. 39 (3–4): 269–271. doi:10.1016/0012-8252(95)90023-3. ISSN   0012-8252.
  4. 1 2 3 4 5 6 7 8 Bhattacharya, B.; Solomatine, D.P. (March 2006). "Machine learning in soil classification". Neural Networks. 19 (2): 186–195. doi:10.1016/j.neunet.2006.01.005. ISSN   0893-6080. PMID   16530382. S2CID   14421859.
  5. 1 2 3 4 5 Sang, Xuejia; Xue, Linfu; Ran, Xiangjin; Li, Xiaoshun; Liu, Jiwen; Liu, Zeyu (2020-02-05). "Intelligent High-Resolution Geological Mapping Based on SLIC-CNN". ISPRS International Journal of Geo-Information. 9 (2): 99. Bibcode:2020IJGI....9...99S. doi: 10.3390/ijgi9020099 . ISSN   2220-9964.
  6. ↑ Si, Lei; Xiong, Xiangxiang; Wang, Zhongbin; Tan, Chao (2020-03-14). "A Deep Convolutional Neural Network Model for Intelligent Discrimination between Coal and Rocks in Coal Mining Face". Mathematical Problems in Engineering. 2020: 1–12. doi: 10.1155/2020/2616510 . ISSN   1024-123X.
  7. 1 2 3 4 5 6 7 8 9 Marjanović, Miloš; Kovačević, Miloš; Bajat, Branislav; Voženílek, Vít (November 2011). "Landslide susceptibility assessment using SVM machine learning algorithm". Engineering Geology. 123 (3): 225–234. Bibcode:2011EngGe.123..225M. doi:10.1016/j.enggeo.2011.09.006. ISSN   0013-7952.
  8. ↑ Merembayev, Timur; Yunussov, Rassul; Yedilkhan, Amirgaliyev (November 2018). "Machine Learning Algorithms for Classification Geology Data from Well Logging". 2018 14th International Conference on Electronics Computer and Computation (ICECCO). IEEE. pp. 206–212. doi:10.1109/icecco.2018.8634775. ISBN   978-1-7281-0132-3. S2CID   59620103.
  9. ↑ De'ath, Glenn; Fabricius, Katharina E. (November 2000). "Classification and Regression Trees: A Powerful Yet Simple Technique for Ecological Data Analysis". Ecology. 81 (11): 3178–3192. doi:10.1890/0012-9658(2000)081[3178:cartap]2.0.co;2. ISSN   0012-9658.
  10. 1 2 3 4 5 Thessen, Anne (2016-06-27). "Adoption of Machine Learning Techniques in Ecology and Earth Science". One Ecosystem. 1: e8621. Bibcode:2016OneEc...1E8621T. doi: 10.3897/oneeco.1.e8621 . ISSN   2367-8194.
  11. ↑ Zhao, Kaiguang; Popescu, Sorin; Meng, Xuelian; Pang, Yong; Agca, Muge (August 2011). "Characterizing forest canopy structure with lidar composite metrics and machine learning". Remote Sensing of Environment. 115 (8): 1978–1996. Bibcode:2011RSEnv.115.1978Z. doi:10.1016/j.rse.2011.04.001. ISSN   0034-4257.
  12. ↑ Lawler, Joshua J.; White, Denis; Neilson, Ronald P.; Blaustein, Andrew R. (2006-06-26). "Predicting climate-induced range shifts: model differences and model reliability". Global Change Biology. 12 (8): 1568–1584. Bibcode:2006GCBio..12.1568L. CiteSeerX   10.1.1.582.9206 . doi:10.1111/j.1365-2486.2006.01191.x. ISSN   1354-1013. S2CID   37416127.
  13. ↑ Tartakovsky, Daniel M. (2004). "Delineation of geologic facies with statistical learning theory". Geophysical Research Letters. 31 (18). Bibcode:2004GeoRL..3118502T. CiteSeerX   10.1.1.146.5147 . doi:10.1029/2004gl020864. ISSN   0094-8276. S2CID   16256805.
  14. ↑ Hurtt, George C.; Dubayah, Ralph; Drake, Jason; Moorcroft, Paul R.; Pacala, Stephen W.; Blair, J. Bryan; Fearon, Matthew G. (June 2004). "Beyond Potential Vegetation: Combining Lidar Data and a Height-Structured Model for Carbon Studies". Ecological Applications. 14 (3): 873–883. Bibcode:2004EcoAp..14..873H. doi:10.1890/02-5317. ISSN   1051-0761.
  15. ↑ Lawler, Joshua J.; White, Denis; Neilson, Ronald P.; Blaustein, Andrew R. (2006-06-26). "Predicting climate-induced range shifts: model differences and model reliability". Global Change Biology. 12 (8): 1568–1584. Bibcode:2006GCBio..12.1568L. CiteSeerX   10.1.1.582.9206 . doi:10.1111/j.1365-2486.2006.01191.x. ISSN   1354-1013. S2CID   37416127.
  16. ↑ Akpokodje, E. G. (June 1979). "The importance of engineering geological mapping in the development of the Niger delta basin". Bulletin of the International Association of Engineering Geology. 19 (1): 101–108. Bibcode:1979BIAEG..19..101A. doi:10.1007/bf02600459. ISSN   1435-9529. S2CID   129112606.
  17. 1 2 3 Costa, Iago; Tavares, Felipe; Oliveira, Junny (April 2019). "Predictive lithological mapping through machine learning methods: a case study in the Cinzento Lineament, Carajás Province, Brazil". Journal of the Geological Survey of Brazil. 2 (1): 26–36. doi: 10.29396/jgsb.2019.v2.n1.3 . ISSN   2595-1939. S2CID   134822423.
  18. 1 2 3 4 Latifovic, Rasim; Pouliot, Darren; Campbell, Janet (2018-02-16). "Assessment of Convolution Neural Networks for Surficial Geology Mapping in the South Rae Geological Region, Northwest Territories, Canada". Remote Sensing. 10 (2): 307. Bibcode:2018RemS...10..307L. doi: 10.3390/rs10020307 . ISSN   2072-4292.
  19. 1 2 3 4 Culverhouse, PF; Williams, R; Reguera, B; Herry, V; González-Gil, S (2003). "Do experts make mistakes? A comparison of human and machine identification of dinoflagellates". Marine Ecology Progress Series. 247: 17–25. Bibcode:2003MEPS..247...17C. doi: 10.3354/meps247017 . ISSN   0171-8630.
  20. 1 2 Loyola-Gonzalez, Octavio (2019). "Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View". IEEE Access. 7: 154096–154113. Bibcode:2019IEEEA...7o4096L. doi: 10.1109/ACCESS.2019.2949286 . ISSN   2169-3536. S2CID   207831043.
  21. 1 2 3 Kumar, Chandan; Chatterjee, Snehamoy; Oommen, Thomas; Guha, Arindam (April 2020). "Automated lithological mapping by integrating spectral enhancement techniques and machine learning algorithms using AVIRIS-NG hyperspectral data in Gold-bearing granite-greenstone rocks in Hutti, India". International Journal of Applied Earth Observation and Geoinformation. 86: 102006. Bibcode:2020IJAEO..8602006K. doi: 10.1016/j.jag.2019.102006 . ISSN   0303-2434. S2CID   210040191.
  22. ↑ "Geologic mapping (UB) - AAPG Wiki". wiki.aapg.org. Retrieved 2024-06-27.
  23. 1 2 Harvey, A. S.; Fotopoulos, G. (2016-06-23). "Geological Mapping Using Machine Learning Algorithms". ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. XLI-B8: 423–430. doi: 10.5194/isprsarchives-xli-b8-423-2016 . ISSN   2194-9034.
  24. ↑ Mattikalli, N (January 1997). "Soil color modeling for the visible and near-infrared bands of Landsat sensors using laboratory spectral measurements". Remote Sensing of Environment. 59 (1): 14–28. Bibcode:1997RSEnv..59...14M. doi:10.1016/s0034-4257(96)00075-2. ISSN   0034-4257.
  25. ↑ Radford, D. D., Cracknell, M. J., Roach, M. J., & Cumming, G. V. (2018). Geological mapping in western Tasmania using radar and random forests. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(9), 3075-3087.
  26. ↑ Wang, Y., Ksienzyk, A. K., Liu, M., & Brönner, M. (2021). Multigeophysical data integration using cluster analysis: assisting geological mapping in Trøndelag, Mid-Norway. Geophysical Journal International, 225(2), 1142-1157.
  27. ↑ "Phillips River landslide hazard mapping project", Landslide Risk Management, CRC Press, pp. 457–466, 2005-06-30, doi:10.1201/9781439833711-28, ISBN   9780429151354 , retrieved 2021-11-12
  28. 1 2 Chauhan, S., Sharma, M., Arora, M. K., & Gupta, N. K. (2010). Landslide susceptibility zonation through ratings derived from artificial neural network. International Journal of Applied Earth Observation and Geoinformation, 12(5), 340-350.
  29. 1 2 Biswajeet, Pradhan; Saro, Lee (November 2007). "Utilization of Optical Remote Sensing Data and GIS Tools for Regional Landslide Hazard Analysis Using an Artificial Neural Network Model". Earth Science Frontiers. 14 (6): 143–151. Bibcode:2007ESF....14..143B. doi:10.1016/s1872-5791(08)60008-1. ISSN   1872-5791.
  30. ↑ Dou, Jie; Yamagishi, Hiromitsu; Pourghasemi, Hamid Reza; Yunus, Ali P.; Song, Xuan; Xu, Yueren; Zhu, Zhongfan (2015-05-19). "An integrated artificial neural network model for the landslide susceptibility assessment of Osado Island, Japan". Natural Hazards. 78 (3): 1749–1776. Bibcode:2015NatHa..78.1749D. doi:10.1007/s11069-015-1799-2. ISSN   0921-030X. S2CID   51960414.
  31. 1 2 Kawabata, Daisaku; Bandibas, Joel (December 2009). "Landslide susceptibility mapping using geological data, a DEM from ASTER images and an Artificial Neural Network (ANN)". Geomorphology. 113 (1–2): 97–109. Bibcode:2009Geomo.113...97K. doi:10.1016/j.geomorph.2009.06.006. ISSN   0169-555X.
  32. ↑ "International society for rock mechanics commission on standardization of laboratory and field tests". International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts. 15 (6): 319–368. December 1978. doi:10.1016/0148-9062(78)91472-9. ISSN   0148-9062.
  33. 1 2 3 4 5 6 7 Byun, Hoon; Kim, Jineon; Yoon, Dongyoung; Kang, Il-Seok; Song, Jae-Joon (2021-07-08). "A deep convolutional neural network for rock fracture image segmentation". Earth Science Informatics. 14 (4): 1937–1951. Bibcode:2021EScIn..14.1937B. doi:10.1007/s12145-021-00650-1. ISSN   1865-0473. S2CID   235762914.
  34. ↑ Repasky, Kevin (2014-03-31). Development and Deployment of a Compact Eye-Safe Scanning Differential absorption Lidar (DIAL) for Spatial Mapping of Carbon Dioxide for Monitoring/Verification/Accounting at Geologic Sequestration Sites (Report). doi:10.2172/1155030. OSTI   1155030.
  35. 1 2 Bellante, G.J.; Powell, S.L.; Lawrence, R.L.; Repasky, K.S.; Dougher, T.A.O. (March 2013). "Aerial detection of a simulated CO2 leak from a geologic sequestration site using hyperspectral imagery". International Journal of Greenhouse Gas Control. 13: 124–137. Bibcode:2013IJGGC..13..124B. doi:10.1016/j.ijggc.2012.11.034. ISSN   1750-5836.
  36. 1 2 3 4 5 6 7 Bateson, L.; Vellico, M.; Beaubien, S.; Pearce, J.; Annunziatellis, A.; Ciotoli, G.; Coren, F.; Lombardi, S.; Marsh, S. (July 2008). "The application of remote-sensing techniques to monitor CO2-storage sites for surface leakage: Method development and testing at Latera (Italy) where naturally produced CO2 is leaking to the atmosphere". International Journal of Greenhouse Gas Control. 2 (3): 388–400. Bibcode:2008IJGGC...2..388B. doi:10.1016/j.ijggc.2007.12.005. ISSN   1750-5836.
  37. 1 2 Bieniawski, Z. T. (1988), "The Rock Mass Rating (RMR) System (Geomechanics Classification) in Engineering Practice", Rock Classification Systems for Engineering Purposes, West Conshohocken, PA: ASTM International, pp. 17–17–18, doi:10.1520/stp48461s, ISBN   978-0-8031-6663-9 , retrieved 2021-11-12
  38. 1 2 3 4 5 6 7 Chen, Jiayao; Zhou, Mingliang; Zhang, Dongming; Huang, Hongwei; Zhang, Fengshou (March 2021). "Quantification of water inflow in rock tunnel faces via convolutional neural network approach". Automation in Construction. 123: 103526. doi:10.1016/j.autcon.2020.103526. ISSN   0926-5805. S2CID   233849934.
  39. ↑ Coerts, Alfred (1996). Analysis of static cone penetration test data for subsurface modelling : a methodology. Koninklijk Nederlands Aardrijkskundig Genootschap/Faculteit Ruimtelijke Wetenschappen Universiteit Utrecht. ISBN   90-6809-230-8. OCLC   37725852.
  40. 1 2 3 4 5 Zhang, Ye; Wang, Gang; Li, Mingchao; Han, Shuai (2018-12-04). "Automated Classification Analysis of Geological Structures Based on Images Data and Deep Learning Model". Applied Sciences. 8 (12): 2493. doi: 10.3390/app8122493 . ISSN   2076-3417.
  41. 1 2 3 Li, Zefeng; Meier, Men-Andrin; Hauksson, Egill; Zhan, Zhongwen; Andrews, Jennifer (2018-05-28). "Machine Learning Seismic Wave Discrimination: Application to Earthquake Early Warning". Geophysical Research Letters. 45 (10): 4773–4779. Bibcode:2018GeoRL..45.4773L. doi: 10.1029/2018gl077870 . ISSN   0094-8276. S2CID   54926314.
  42. 1 2 Rouet-Leduc, Bertrand; Hulbert, Claudia; Lubbers, Nicholas; Barros, Kipton; Humphreys, Colin J.; Johnson, Paul A. (2017-09-22). "Machine Learning Predicts Laboratory Earthquakes". Geophysical Research Letters. 44 (18): 9276–9282. arXiv: 1702.05774 . Bibcode:2017GeoRL..44.9276R. doi:10.1002/2017gl074677. ISSN   0094-8276. S2CID   118842086.
  43. ↑ Kirchner, James W. (March 2006). "Getting the right answers for the right reasons: Linking measurements, analyses, and models to advance the science of hydrology". Water Resources Research. 42 (3). Bibcode:2006WRR....42.3S04K. doi:10.1029/2005wr004362. ISSN   0043-1397. S2CID   2089939.
  44. 1 2 Petty, T.R.; Dhingra, P. (2017-08-08). "Streamflow Hydrology Estimate Using Machine Learning (SHEM)". JAWRA Journal of the American Water Resources Association. 54 (1): 55–68. doi:10.1111/1752-1688.12555. ISSN   1093-474X. S2CID   135100027.
  45. ↑ Karpatne, Anuj; Ebert-Uphoff, Imme; Ravela, Sai; Babaie, Hassan Ali; Kumar, Vipin (2019-08-01). "Machine Learning for the Geosciences: Challenges and Opportunities". IEEE Transactions on Knowledge and Data Engineering. 31 (8): 1544–1554. arXiv: 1711.04708 . doi:10.1109/tkde.2018.2861006. ISSN   1041-4347. S2CID   42476116.
  46. ↑ Farrar, Donald E.; Glauber, Robert R. (February 1967). "Multicollinearity in Regression Analysis: The Problem Revisited". The Review of Economics and Statistics. 49 (1): 92. doi:10.2307/1937887. hdl: 1721.1/48530 . ISSN   0034-6535. JSTOR   1937887.
  47. ↑ Taghizadeh-Mehrjardi, R.; Nabiollahi, K.; Kerry, R. (March 2016). "Digital mapping of soil organic carbon at multiple depths using different data mining techniques in Baneh region, Iran". Geoderma. 266: 98–110. Bibcode:2016Geode.266...98T. doi:10.1016/j.geoderma.2015.12.003. ISSN   0016-7061.
  48. ↑ Delibasic, Boris; Vukicevic, Milan; Jovanovic, Milos; Suknovic, Milija (August 2013). "White-Box or Black-Box Decision Tree Algorithms: Which to Use in Education?". IEEE Transactions on Education. 56 (3): 287–291. Bibcode:2013ITEdu..56..287D. doi:10.1109/te.2012.2217342. ISSN   0018-9359. S2CID   11792899.
  49. ↑ Merghadi, Abdelaziz; Yunus, Ali P.; Dou, Jie; Whiteley, Jim; ThaiPham, Binh; Bui, Dieu Tien; Avtar, Ram; Abderrahmane, Boumezbeur (August 2020). "Machine learning methods for landslide susceptibility studies: A comparative overview of algorithm performance". Earth-Science Reviews. 207: 103225. Bibcode:2020ESRv..20703225M. doi:10.1016/j.earscirev.2020.103225. ISSN   0012-8252. S2CID   225816933.
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.