+36 70 203-3120 | agrowebsystem@gmail.com | Blog | Contact

7 ways GIS eliminates guesswork in agriculture

  • 253

Artificial intelligence in agriculture has been fostered by the general development of technology in recent decades.

The application of artificial intelligence in agriculture is about analysing land, displaying field data on maps and putting that data to work. With artificial intelligence, precision farming enables informed decisions and actions that allow farmers to get the most out of each hectare without harming the environment.

Speaking of tools, agricultural GIS technology relies on satellites, aircraft, drones and sensors. These tools are used to take images and link them to maps and non-visualized data. The result is a map that shows crop location and health, topography, soil type, fertilization, and similar information.

There are many applications of geoinformatics in agriculture.

Learn more about the following applications and uses of geoinformatics in agriculture:

Yield forecasting

Accurate yield forecasting can help governments ensure food security and businesses forecast profits and plan budgets. Recent advances in technology that combine satellites, sensing, big data and artificial intelligence can make these forecasts possible.

One of the most profound techniques in this area is convolutional neural networks (ConvNets or CNNs). A ConvNet is a deep learning algorithm that is taught to identify the productivity of a plant. Developers train this algorithm by feeding it images of plants whose yields are already known to find productivity patterns. CNN’s accuracy is about 82%.

Source of image above: Sustainability and Artificial Intelligence Lab, Stanford University

Monitoring crop health

Manually monitoring crop health across multiple acres is the least efficient solution. That’s where remote sensing combined with GIS comes to the rescue in agriculture.

Main satellite imagery and input information can be paired to assess environmental conditions such as humidity, air temperature, surface conditions and more across the field. Based on GIS, precision farming can enhance such assessments and help decide which crops need more attention.

A more sophisticated approach uses imaging sensors on satellites and aircraft to monitor crop temperatures. If the temperature is higher than normal, it could indicate disease, infection or inadequate irrigation.

Neural networks such as CNN, Radial Basis Function Network (RBFN), Perceptron and others can also be useful in assessing crop health. Algorithms can analyze images for unhealthy patterns.

Livestock Monitoring

The simplest application of agricultural GIS software in livestock production is to track the movements of individual animals. This helps farmers locate them on the farm and track their health, fertility and nutrition. The GIS services that make this possible consist of trackers installed on the animals and a mobile device that receives and displays information from these trackers.

Here is an example. You want to track the weight of your beef cattle. Each animal has a tracker on its ear or neck. Each time you step on the digital scale, the scale reads the ID of that animal and assigns a new value to the ID in the system.

You do not have to manually enter this data. Meanwhile, if there is an alarming change in the animal’s weight, you can quickly locate the animal and check its health.

There are more interesting use cases for agricultural GIS software, such as preventing wolf and cattle encounters. There are ambiguous spatial features that affect the distribution of wildlife in an area, including wolves. Undesirable encounters could be reduced by understanding these subtle peculiarities, which could be achieved by using AI and GIS in combination in agriculture.

Insect and pest control

Invasions of harmful insects and pests, or infestations, cause severe damage to agriculture. Overhead visibility can enable accurate, timely alerts to prevent this from happening.

In the ozone layer, even high-resolution imagery may not give visible early signs of infestation.

The alternative would be to use artificial intelligence. Develop a neural network and train it using deep learning algorithms. During training, the neural network is fed images of infected areas, and the network learns to find patterns indicative of infection. You can then feed the network with satellite images of the area you want to analyze.

As mentioned earlier, in agriculture, you can use remote sensing along with geospatial technology to monitor crop temperatures. Plants respond to infestation by heating up as they no longer get enough water or nutrients.

Irrigation Control

Keeping an eye on each crop getting enough water in vast areas of land is a challenging task, but in agriculture, geospatial technology can easily solve it.

Aircraft and satellites equipped with high-resolution cameras take images that can be used by artificial intelligence algorithms to calculate the water load of individual crops and detect visual patterns underlying water scarcity.

Pair these images with maps of your water supply system and you can see how well your current irrigation system is working.

Flood, erosion and drought control

Combining GIS and agriculture can help you prevent, assess and mitigate the negative impacts of destructive natural phenomena.

Use flood mapping techniques to identify areas prone to flooding. You will need to collect data such as past flooding, field surveys and satellite imagery. Use this data to create a dataset that you can use to train a neural network to identify and map flood risks and create an ultimate disaster

mitigation tool.

If you need to study soil erosion susceptibility, you can pair Universal Soil Loss Equation (USLE) with GIS and remote sensing. Run satellite imagery with spectral analysis to verify USLE factors and verify these images with field observations. As a result, you can generate a map showing the extent of soil degradation across the entire area.

Similar GIS solutions can be used in agriculture to monitor drought.

Agricultural automation

Seeders, smart irrigation systems, driverless harvesters and weed-killing robots are the inevitable future. You could equip each machine with sophisticated sensors, but why do that when you can connect them to an integrated GIS system?

(This is not to say that automated vehicles don’t need sensors – they do.)

GIS in agriculture can provide accurate maps, including all the information you need about your field crops. Such maps are called task maps or application maps. They are used by intelligent machines to manage the field.

Here is an example of how GIS solutions can work in agriculture. If a GIS system detects a weed infestation, it will assign a “Weed control needed” label to the area. The weeding robot reads the label and adds that area to its task list.

In addition to providing signals to machines, task maps can help unskilled workers do their jobs more efficiently.


When searching the Internet for agricultural use cases for GIS, you can find articles and studies dating back to the early 1990s. The goals of agriculture haven’t changed much since then – and neither have the problems that GIS is expected to solve.

Format: https://intellias.com/gis-in-agriculture/