Revolutionizing Farming using AI

By -

Revolutionizing Farming using AI

Introduction:

The data from FAO (Food and Agriculture Organization) clearly shows that by 2050 the world's population will increase by 2 billion. The total land area under cultivation would be only 4% by that time. This will eventually add stress to existing farming techniques and research methodology. We not only need to increase the yield but also a severe need to increase the current speed of agriculture research. The increasing effects of global warming add more fuel to this problem. Excessive use of pesticides and insecticides in the past several decades has deteriorated the land quality, which eventually affected the crop quality. Intense crop breeding s required that can survive the adversities in the future. 

All this in the end means that we need to revolutionize farming practices around the globe. The possible new "green" revolution will be different from the previous one that happened a few decades back. This time computers and specifically artificial intelligence will play a major role in the revolution. The work has already been started by numerous researchers around the globe in this field. Here I have highlighted two major ongoing research fields that use AI. 

1. Monitoring crop Health: 

The poor health of crops is a major reason for crop failure. Traditionally, crop health detection is done by observing the colour of the leaf and the presence of spots. However, these time-consuming techniques are now replaced by computers and drones. The drone-based aerial imaging can easily monitor crop health across a large field. This has guided farmers to use pesticides and other chemicals only in the required area. Drones would scan the whole farm with a particular crop. Then the captured data and images are sent for advanced processing, where the AI plays its role. These advanced image processing techniques developed precisely for the agriculture market can easily and efficiently detect various diseases in a particular crop.   

This effective field scanning method has also reduced the spread of diseases in the crops. A group of researchers including Xanthoula Pantazi, Jon West and Roberto Oberti has successfully developed an algorithm for wheat that can easily differentiate between healthy and diseased crops. The algorithm successfully identified nitrogen-stressed, rust-infected yellow crops using self-imaging techniques.   

Drones have proved to be a very successful medium to improve farming techniques. Today, the total drone-based solution market for agriculture is about 32 billion dollars. Drones are used not only for disease detection but also for land quality measurement, water level detection, precise seed cultivation and yield management. Efficient land scanning can help to predict the best fit crop for that particular land, which will eventually positively affect the crop yield. 

2. Crop Breeding:

One of the most complicated and time-consuming processes in the field of agriculture research is crop breeding. With the increasing demands, researchers don't think they have time for typical breeding techniques. Researchers are shifting towards computers for effective breeding predictions and computations. Using AI, breeders can easily access which particular crops grow faster in a particular climate condition or the land. This effective breeding is expected to increase yield and even crop quality. 

The reason why we can integrate breeding techniques with AI is that plant breeding not only depends on genetics but also on mathematics. Various statistical data are also needed for successful plant breeding. Since last two decades, computers were getting introduced in the breeding process. However, with the recent advancements in AI, its usage is getting more significant.   

Crop breeder and geneticist Steven Tanksley firmly believe that AI has made the complicated breeding process much easier. It has overcome various problems that were faced in a typical approach. For example, for a successful breed, the breeder must decide the genetic lines that will optimize the crop. Wheat, for example, has more than 200 genetic lines. The breeder must decide the most optimal lines to breed together. It's very difficult to decide the correct pair of lines and sometimes the number of possible pairs is more than the stars in the universe

This puzzle is now solved up to a certain extent by optimization algorithms. These algorithms are developed to decide the quickest path to find the optimal pairs in the shortest possible time. Along with the genetic lines, breeders also include different traits like DNA sequences, drought tolerance, disease resistance etc. The algorithm calculates which gene is associated with which trait and determines the optimal combination o genes. The algorithm also determines which lines to cross together.

This AI technique has also attracted large seed manufacturing companies. Various private seed manufacturers are conducting their independent breeding research using AI. Both the above methods, crop monitoring and breeding techniques using AI have successfully gained the interest of private firms across the globe. However, apart from these two methods, AI is getting involved in more and more agriculture practices. Irrigation techniques are also revolutionizing with AI. One can easily confirm with the ongoing trend that AI is the best possible way to bring change to agriculture. Just as the industrial revolution mechanized farming, today's AI era will computerized farming.        

Comments

Post a Comment

Please do not use foul language while commenting. We will appreciate your suggestions and reviews in the comments.

Read Also

Assisting Neuroimaging through DL

By -
Image
Introduction: In recent years, neuroimaging has been a research attraction, especially due to fMRI (Functional Magnetic Resonance Imaging) advancements. The fMRI data comprises of often several individuals. This data is used by researchers to study the association between the cognitive states of an individual and the underlying brain activities. The fMRI data used for neuroimaging is ideally suited for deep learning applications. The large, structured datasets of fMRI can be used for representation-learning methods of the DL. Generally, DL can be defined as a learning method with multiple levels of abstraction, where at each level the input data is transformed by a simple non-linear function which enables the model to recognize complex patterns. With higher-level representation, DL methods can associate a target variable with variable patterns in input data. Also, DL techniques can independently acquire these transformations from the data, eliminating the need for a comprehensive preex
Read more

Marine eDNA Analysis using DL techniques

By -
Image
Introduction Environmental DNA (eDNA) is the genetic information or material released by an organism into its surroundings through activities like skin shedding, mucus, urine or other secretions. These materials contain DNA fragments that can be found in soil, water or air samples. The concept of eDNA is based on the fact that organisms constantly leave organic traces behind them. By analysing the eDNA, researchers can detect the presence of any species in that area. This method is a valuable technique for biodiversity monitoring and ecological research.    Unlike traditional methods that involve direct observation or capturing of organisms, eDNA analysis allows researchers to study biodiversity without directly interacting with the species. This non-invasive approach is particularly useful for studying elusive or endangered species. eDNA analysis has been applied in various ecosystems, including freshwater, marine, and terrestrial environments. It is used to study aquatic organisms, t
Read more

Deep Neural Networks for ADMET properties' prediction

By -
Image
Introduction The absorption, distribution, metabolism, excretion and toxicity properties of any compound contributes to its potential as an orally administered drug. A set of criteria defined by Rule of Five or the Pfizer's Rule of Five stats that any compound meeting these criteria are more likely to have ADMET properties. The importance of these properties has increased in modern medicinal chemistry and new machine learning techniques are employed to predict these properties. The predictive ADMET models have helped in discovery of small molecules with improved safety and dose. Deep Neural Networks are showing usefulness in such predictions due to improved computational efficiency, larger datasets and adaption of image processing in the chemistry. Early Models The early DNNs employed showed improved prediction performance. Many researchers raised concerned that this improvement is in fact has no relation with better computational capacity, rather it is result of mere memorizing of
Read more

How Visual Cortex inspired the Convolutional Neural Networks

By -
Image
Introduction Since the 1960s, after the successful development (at least with respect to the existing technologies of that time) of the first perceptron by Frank Rosenblatt, researchers around the world have been trying to make computers more brain-like. In other words, they are constantly trying to develop programs and hardware that work much like our brains. However, creating a machine that thinks and programs like a human brain is still impossible, given the limitations of present technologies. But, we are successful in this direction up to an agreeable extent. The perceptron developed by Rosenblatt can be considered one of the first implementations of neural networks. It was a huge hardware model, rather than a Python program like today's perceptrons.  Rosenblatt's perceptron was a simple binary input-output system, with various limitations. It was not trainable for different patterns, rather but for simple image recognization. The major drawback was its inability to perfor
Read more