Data mining in agriculture

Last updated

Data mining in agriculture is a research topic consisting of the application of data mining and data science techniques to agriculture. Recent technologies are able to provide extensive data on agricultural-related activities, which can then be analyzed in order to find information. [1]

Contents

Applications

Relationship between sprays and fruit defects

Fruit defects are often recorded (for a multitude of reasons, sometimes for insurance reasons when exporting fruit overseas). It may be done manually or through computer vision (detecting surface defects when grading fruit).[ citation needed ] Spray diaries are a legal requirement in many countries and at the very least record the date of spray and the product name. It is known that spraying can have different fruit defects for different fruit. Fungicidal sprays are often used to prevent rots from being expressed on fruit. It is also known that some sprays can cause russeting on apples. [2] Currently much of this knowledge comes anecdotally, however some efforts have been in regards to the use of data mining in horticulture. [3]

Prediction of problematic wine fermentations

The fermentation process of wine impacts the productivity of wine-related industries as well as the quality of the wine. Data science techniques, such as the k-means algorithm, [4] and classification techniques based on the concept of biclustering [5] have been used to study the process of fermentation in order to predict problematic wine fermentations. These methods differ from techniques where a classification of different kinds of wine is performed. See the wiki page Classification of wine for more details.

Predicting metabolizable energy of poultry feed using group method of data handling-type neural network

A group method of data handling-type neural network (GMDH-type network) with an evolutionary method of genetic algorithm was used to predict the metabolizable energy of feather meal and poultry offal meal based on their protein, fat, and ash content. Published data samples were collected from literature and used to train a GMDH-type network model. The novel modeling of GMDH-type network with an evolutionary method of genetic algorithm can be used to predict the metabolizable energy of poultry feed samples based on their chemical content. [6] It is also reported that the GMDH-type network may be used to accurately estimate the poultry performance from their dietary nutrients such as dietary metabolizable energy, protein and amino acids. [7]

Detection of diseases from sounds issued by animals

The detection of diseases in farms can positively impact the productivity of the farm by reducing contamination to other animals. Moreover, the early detection of the diseases can allow the farmer to treat and isolate the animal as soon as the disease appears. Sounds issued by pigs, such as coughs, can be analyzed for the detection of diseases. A computational system is under development which is able to monitor pig sounds by microphones installed in the farm, and which is also able to discriminate among the different sounds that can be detected. [8]

Growth of sheep from genes polymorphism using artificial intelligence

Polymerase chain reaction-single strand conformation polymorphism (PCR-SSCP) method was used to determine the growth hormone (GH), leptin, calpain, and calpastatin polymorphism in Iranian Balochi male sheep. An artificial neural network (ANN) model was developed to describe average daily gain (ADG) in lambs from input parameters of GH, leptin, calpain, and calpastatin polymorphism, birth weight, and birth type. The results revealed that the ANN-model is an appropriate tool to recognize the patterns of data to predict lamb growth in terms of ADG given specific genes polymorphism, birth weight, and birth type. The platform of PCR-SSCP approach and ANN-based model analyses may be used in molecular marker-assisted selection and breeding programs to design a scheme in enhancing the efficacy of sheep production. [9]

Sorting apples by watercourse

Before going to market, apples are checked and the ones showing some defects are removed. However, there are also invisible defects that can spoil the apple flavor and look. An example of invisible defect is an internal apple disorder that can affect the longevity of the fruit called a watercore. Apples with slight or mild watercourse are sweeter, but apples with moderate to severe degree of watercore cannot be stored for any length of time. Moreover, a few fruits with severe watercore could spoil a whole batch of apples. For this reason, a computational system is under study which takes X-ray photographs of the fruit while they run on conveyor belts, and which is also able to analyse (by data mining techniques) the taken pictures and estimate the probability that the fruit contains watercores. [10]

Optimizing pesticide use by data mining

Recent studies by agriculture researchers in Pakistan showed that attempts of cotton crop yield maximization through pro-pesticide state policies have led to a dangerously high pesticide use. These studies have reported a negative correlation between pesticide use and crop yield in Pakistan. Hence excessive use (or abuse) of pesticides is harming the farmers with adverse financial, environmental and social impacts. By data mining the cotton Pest Scouting data along with the meteorological recordings it was shown that how pesticide use can be optimized (reduced). Clustering of data revealed interesting patterns of farmer practices along with pesticide use dynamics and hence help identify the reasons for this pesticide abuse. [11]

Explaining pesticide abuse by data mining

To monitor cotton growth, different government departments and agencies in Pakistan have been recording pest scouting, agriculture and metrological data for decades. Coarse estimates of just the cotton pest scouting data recorded stands at around 1.5 million records, and growing. The primary agro-met data recorded has never been digitized, integrated or standardized to give a complete picture, and hence cannot support decision making, thus requiring an Agriculture Data Warehouse. Creating a novel Pilot Agriculture Extension Data Warehouse followed by analysis through querying and data mining some interesting discoveries were made, such as pesticides sprayed at the wrong time, wrong pesticides used for the right reasons and temporal relationship between pesticide usage and day of the week. [12]

Analyzing chicken performance data by neural network models

A platform of artificial neural network-based models with sensitivity analysis and optimization algorithms was used successfully to integrate published data on the responses of broiler chickens to threonine. Analyses of the artificial neural network models for weight gain and feed efficiency from a compiled data set suggested that the dietary protein concentration was more important than the threonine concentration. The results revealed that a diet containing 18.69% protein and 0.73% threonine may lead to producing optimal weight gain, whereas the optimal feed efficiency may be achieved with a diet containing 18.71% protein and 0.75% threonine. [13]

Literature

There are a few precision agriculture journals, such as Springer's Precision Agriculture or Elsevier's Computers and Electronics in Agriculture, but those are not exclusively devoted to data mining in agriculture.

Related Research Articles

<span class="mw-page-title-main">Vinegar</span> Liquid consisting mainly of acetic acid and water

Vinegar is an aqueous solution of acetic acid and trace compounds that may include flavorings. Vinegar typically contains from 5% to 18% acetic acid by volume. Usually, the acetic acid is produced by a double fermentation, converting simple sugars to ethanol using yeast and ethanol to acetic acid using acetic acid bacteria. Many types of vinegar are made, depending on source materials. The product is now mainly used in the culinary arts as a flavorful, acidic cooking ingredient or in pickling. Various types are used as condiments or garnishes, including balsamic vinegar and malt vinegar.

<span class="mw-page-title-main">Threonine</span> Amino acid

Threonine is an amino acid that is used in the biosynthesis of proteins. It contains an α-amino group, a carboxyl group, and a side chain containing a hydroxyl group, making it a polar, uncharged amino acid. It is essential in humans, meaning the body cannot synthesize it: it must be obtained from the diet. Threonine is synthesized from aspartate in bacteria such as E. coli. It is encoded by all the codons starting AC.

<span class="mw-page-title-main">Winemaking</span> Production of wine

Winemaking, wine-making, or vinification is the production of wine, starting with the selection of the fruit, its fermentation into alcohol, and the bottling of the finished liquid. The history of wine-making stretches over millennia. There is evidence that suggests that the earliest wine production took place in Georgia and Iran around 6000 to 5000 B.C. The science of wine and winemaking is known as oenology. A winemaker may also be called a vintner. The growing of grapes is viticulture and there are many varieties of grapes.

<span class="mw-page-title-main">Fruit wine</span> Fermented beverage made from fruit other than grapes

Fruit wines are fermented alcoholic beverages made from a variety of base ingredients ; they may also have additional flavors taken from fruits, flowers, and herbs. This definition is sometimes broadened to include any alcoholic fermented beverage except beer. For historical reasons, mead, cider, and perry are also excluded from the definition of fruit wine.

<span class="mw-page-title-main">Cider apple</span> Fruit used for making apple cider

Cider apples are a group of apple cultivars grown for their use in the production of cider. Cider apples are distinguished from "cookers" and "eaters", or dessert apples, by their bitterness or dryness of flavour, qualities which make the fruit unpalatable but can be useful in cidermaking. Some apples are considered to occupy more than one category.

<span class="mw-page-title-main">Malathion</span> Chemical compound

Malathion is an organophosphate insecticide which acts as an acetylcholinesterase inhibitor. In the USSR, it was known as carbophos, in New Zealand and Australia as maldison and in South Africa as mercaptothion.

<span class="mw-page-title-main">Malolactic fermentation</span> Process in winemaking

Malolactic conversion is a process in winemaking in which tart-tasting malic acid, naturally present in grape must, is converted to softer-tasting lactic acid. Malolactic fermentation is most often performed as a secondary fermentation shortly after the end of the primary fermentation, but can sometimes run concurrently with it. The process is standard for most red wine production and common for some white grape varieties such as Chardonnay, where it can impart a "buttery" flavor from diacetyl, a byproduct of the reaction.

<span class="mw-page-title-main">Kilju</span> Finnish home made alcoholic beverage

Kilju is the Finnish word for home made alcoholic beverage typically made of sugar, yeast, and water. The ABV is around 15–17%, and since it does not contain a sweet reserve it is completely dry. Crude fermented water may be distilled to moonshine. Kilju for consumption is clarified to avoid wine fault. It is a flax-colored alcoholic beverage with no discernible taste other than that of ethanol. It can be used as an ethanol base for drink mixers.

Neural network software is used to simulate, research, develop, and apply artificial neural networks, software concepts adapted from biological neural networks, and in some cases, a wider array of adaptive systems such as artificial intelligence and machine learning.

<span class="mw-page-title-main">Chicken as food</span> Type of meat

Chicken is the most common type of poultry in the world. Owing to the relative ease and low cost of raising chickens—in comparison to mammals such as cattle or hogs—chicken meat and chicken eggs have become prevalent in numerous cuisines.

Patulin is an organic compound classified as a polyketide. It is named after the fungus from which it was isolated, Penicillium patulum. It is a white powder soluble in acidic water and in organic solvents. It is a lactone that is heat-stable, so it is not destroyed by pasteurization or thermal denaturation. However, stability following fermentation is lessened. It is a mycotoxin produced by a variety of molds, in particular, Aspergillus and Penicillium and Byssochlamys. Most commonly found in rotting apples, the amount of patulin in apple products is generally viewed as a measure of the quality of the apples used in production. In addition, patulin has been found in other foods such as grains, fruits, and vegetables. Its presence is highly regulated.

<span class="mw-page-title-main">Intensive animal farming</span> Branch of agriculture

Intensive animal farming, industrial livestock production, and macro-farms, also known as factory farming, is a type of intensive agriculture, specifically an approach to animal husbandry designed to maximize production while minimizing costs. To achieve this, agribusinesses keep livestock such as cattle, poultry, and fish at high stocking densities, at large scale, and using modern machinery, biotechnology, and global trade. The main products of this industry are meat, milk and eggs for human consumption.

<span class="mw-page-title-main">Poultry farming</span> Part of animal husbandry

Poultry farming is the form of animal husbandry which raises domesticated birds such as chickens, ducks, turkeys and geese to produce meat or eggs for food. Poultry – mostly chickens – are farmed in great numbers. More than 60 billion chickens are killed for consumption annually. Chickens raised for eggs are known as layers, while chickens raised for meat are called broilers.

<span class="mw-page-title-main">Preserved lemon</span> Type of pickle

Preserved lemon or lemon pickle is a condiment that is common in the cuisines of Indian subcontinent and Morocco. It was also found in 18th-century English cuisine.

<span class="mw-page-title-main">Alexey Ivakhnenko</span> Soviet–Ukrainian mathematician and computer scientist

Alexey Ivakhnenko was a Soviet and Ukrainian mathematician most famous for developing the group method of data handling (GMDH), a method of inductive statistical learning.

Group method of data handling (GMDH) is a family of inductive algorithms for computer-based mathematical modeling of multi-parametric datasets that features fully automatic structural and parametric optimization of models.

<span class="mw-page-title-main">Cider</span> Fermented alcoholic beverage from apple juice

Cider is an alcoholic beverage made from the fermented juice of apples. Cider is widely available in the United Kingdom and Ireland. The UK has the world's highest per capita consumption, as well as the largest cider-producing companies. Ciders from the South West of England are generally higher in alcoholic content. Cider is also popular in many Commonwealth countries, such as India, South Africa, Canada, Australia, New Zealand, and New England. As well as the UK and its former colonies, cider is popular in Portugal, France, Friuli, and northern Spain. Germany also has its own types of cider with Rhineland-Palatinate and Hesse producing a particularly tart version known as Apfelwein. In the U.S. and Canada, varieties of alcoholic cider are often called hard cider to distinguish it from non-alcoholic apple cider or "sweet cider", also made from apples. In Canada, cider cannot contain less than 2.5% or over 13% absolute alcohol by volume.

Adulteration is a legal offense and when the food fails to meet the legal standards set by the government, it is said to have been Adulterated Food. One form of adulteration is the addition of another substance to a food item in order to increase the quantity of the food item in raw form or prepared form, which results in the loss of the actual quality of the food item. These substances may be either available food items or non-food items. Among meat and meat products some of the items used to adulterate are water or ice, carcasses, or carcasses of animals other than the animal meant to be consumed. In the case of seafood, adulteration may refer to species substitution (mislabeling), which replaces the species identified on the product label with another species, or undisclosed processing methods, in which treatments such as additives, excessive glazing, or short-weighting are not disclosed to the consumer.

A chicken harvester is a machine used in poultry farming to gather chickens for slaughter.

<span class="mw-page-title-main">Feed manufacturing</span> Production of animal feed

Feed manufacturing refers to the process of producing animal feed from raw agricultural products. Fodder produced by manufacturing is formulated to meet specific animal nutrition requirements for different species of animals at different life stages. According to the American Feed Industry Association (AFIA), there are four basic steps:

  1. Receive raw ingredients: Feed mills receive raw ingredients from suppliers. Upon arrival, the ingredients are weighed, tested and analyzed for various nutrients and to ensure their quality and safety.
  2. Create a formula: Nutritionists work side by side with scientists to formulate nutritionally sound and balanced diets for livestock, poultry, aquaculture and pets. This is a complex process, as every species has different nutritional requirements.
  3. Mix ingredients: Once the formula is determined, the mill mixes the ingredients to create a finished product.
  4. Package and label: Manufacturers determine the best way to ship the product. If it is prepared for retail, it will be "bagged and tagged," or placed into a bag with a label that includes the product's purpose, ingredients and instructions. If the product is prepared for commercial use, it will be shipped in bulk.

References

  1. Mucherino, A.; Papajorgji, P.J.; Pardalos, P. (2009). Data Mining in Agriculture, Springer.
  2. "Apple russeting". www.extension.umn.edu. Archived from the original on 2016-10-02. Retrieved 2016-10-04.
  3. Hill, M. G.; Connolly, P. G.; Reutemann, P.; Fletcher, D. (2014-10-01). "The use of data mining to assist crop protection decisions on kiwifruit in New Zealand". Computers and Electronics in Agriculture. 108: 250–257. doi:10.1016/j.compag.2014.08.011.
  4. Urtubia, A.; Perez-Correa, J.R.; Meurens, M.; Agosin, E. (2004). "Monitoring Large Scale Wine Fermentations with Infrared Spectroscopy". Talanta. 64 (3): 778–784. doi:10.1016/j.talanta.2004.04.005. PMID   18969672.
  5. Mucherino, A.; Urtubia, A. (2010). "Consistent Biclustering and Applications to Agriculture". IbaI Conference Proceedings, Proceedings of the Industrial Conference on Data Mining (ICDM10), Workshop Data Mining in Agriculture (DMA10), Springer: 105–113.
  6. Ahmadi, H.; Golian, A.; Mottaghitalab, M.; Nariman-Zadeh, N. (2008-09-01). "Prediction Model for True Metabolizable Energy of Feather Meal and Poultry Offal Meal Using Group Method of Data Handling-Type Neural Network". Poultry Science. 87 (9): 1909–1912. doi: 10.3382/ps.2007-00507 . ISSN   0032-5791. PMID   18753461.
  7. Ahmadi, Dr H.; Mottaghitalab, M.; Nariman-Zadeh, N.; Golian, A. (2008-05-01). "Predicting performance of broiler chickens from dietary nutrients using group method of data handling-type neural networks". British Poultry Science. 49 (3): 315–320. doi:10.1080/00071660802136908. ISSN   0007-1668. PMID   18568756. S2CID   205399055.
  8. Chedad, A.; Moshou, D.; Aerts, J.M.; Van Hirtum, A.; Ramon, H.; Berckmans, D. (2001). "Recognition System for Pig Cough based on Probabilistic Neural Networks". Journal of Agricultural Engineering Research. 79 (4): 449–457. doi:10.1006/jaer.2001.0719.
  9. Mojtaba, Tahmoorespur; Hamed, Ahmadi (2012-01-01). "neural network model to describe weight gain of sheep from genes polymorphism, birth weight and birth type". Livestock Science. ISSN   1871-1413.
  10. Schatzki, T.F.; Haff, R.P.; Young, R.; Can, I.; Le, L-C.; Toyofuku, N. (1997). "Defect Detection in Apples by Means of X-ray Imaging". Transactions of the American Society of Agricultural Engineers. 40 (5): 1407–1415. doi:10.13031/2013.21367.
  11. Abdullah, Ahsan; Brobst, Stephen; Pervaiz, Ijaz; Umar, Muhammad; Nisar, Azhar (2004). Learning Dynamics of Pesticide Abuse through Data Mining (PDF). Australasian Workshop on Data Mining and Web Intelligence, Dunedin, New Zealand. Archived from the original (PDF) on 2011-08-14. Retrieved 2010-07-20.
  12. Abdullah, Ahsan; Hussain, Amir (2006). "Data Mining a New Pilot Agriculture Extension Data Warehouse" (PDF). Journal of Research and Practice in Information Technology. 38 (3): 229–249. Archived from the original (PDF) on 2010-09-23.
  13. Ahmadi, H.; Golian, A. (2010-11-01). "The integration of broiler chicken threonine responses data into neural network models". Poultry Science. 89 (11): 2535–2541. doi: 10.3382/ps.2010-00884 . ISSN   0032-5791. PMID   20952719.