Remote sensing and GIS in agriculture
A 2018 research conducted by ESRI shows that 73% of farmers implement Geographic Information Systems (GIS) to monitor their crops. This technology assists them in refining field management, identifying pests and diseases early, and enhancing crop production.
A study in 2020 that the USDA-NASS had, suggests that more than 50 million acres of agricultural land in the United States are surveyed with GIS and remote sensing technology to evaluate soil condition and its compatibility with various crops.
A 2019 analysis from the World Resources Institute indicates that employing precision agriculture through GIS and sensing technologies can lead to a reduction of up to 30% in water consumption and up to 20% in fertilizer usage, aiding in the adoption of more sustainable agricultural methods.
All the data points out that applications of GIS and sensing technologies are successful, and have a promising future in agriculture. So, how can a farmer implement them, and what technical resources are required? Let’s go into more detail.
What remote sensing in agriculture looks like beyond the map
This practical gap between collecting satellite data and using it was the focus of a recent Digital Ag Global podcast episode. Hosts Clyde Graham and Yurii Kovalchuk discussed remote sensing in agriculture with Yevhenii Marchenko, Crop Monitoring Intelligence Specialist at EOS Data Analytics, and Luděk Novák, CEO of Agrinova Consulting.
As Clyde Graham observed, remote sensing can still feel like a “black box” to growers and agribusinesses: a platform displays colorful maps, but users may not know what those colors mean or what action to take. The discussion therefore examined both ends of the remote sensing value chain—from satellite imagery and vegetation indices to agronomic interpretation and field-level decisions.
What is GIS in agriculture?
Integrate remote sensing data with other agricultural management systems, such as IoT devices, GIS platforms, or farm ERPs
What is remote sensing in agriculture? 10 examples of GIS in agriculture
Remote sensing in agriculture refers to the technique of obtaining information about the earth’s surface, including crops, soil conditions, and environmental factors, without making direct contact. This is achieved through sensors mounted on satellites, aircraft, drones, or other platforms that capture data using various parts of the electromagnetic spectrum, such as visible light, infrared, and microwave. Remote sensing technology plays a crucial role in modern agriculture by providing detailed, timely, and accurate information to support decision-making processes. Here are some of the key applications of remote sensing in agriculture:
Crop monitoring and management. Remote sensing allows for the continuous monitoring of crop health, growth stages, and overall vegetation vigor. By analyzing data on reflectance from crops, it can help identify stress factors such as water scarcity, nutrient deficiencies, pest infestations, or disease outbreaks before they become visible to the naked eye.
Soil moisture and condition assessment. Sensors can detect variations in soil moisture and composition, providing valuable information for irrigation management and soil conservation practices. This data helps in applying water and fertilizers more efficiently, tailored to the specific needs of different crop zones.
Yield prediction and estimation. By analyzing historical and current remote sensing data, models can be developed to predict crop yields. This information is invaluable for farmers, policymakers, and supply chain stakeholders for planning and decision-making.
Precision agriculture. Remote sensing is a key component of precision agriculture, enabling the creation of detailed maps of variables such as crop health, soil conditions, and moisture levels. These maps can then guide variable-rate technology (VRT) equipment to apply the right amount of water, fertilizers, and pesticides where they are needed most, optimizing inputs and reducing environmental impact.
Land use and cover mapping. It provides detailed information on land use patterns and changes over time, helping in the planning and management of agricultural lands, detecting shifts in agricultural practices, and assessing the impacts of policies and interventions.
Drought and water stress detection. Remote sensing can identify areas affected by drought or water stress early on. This allows for timely interventions to mitigate the impact on crops and optimize water use.
Pest and disease surveillance. Changes in plant reflectance can indicate the presence of pests or disease. Remote sensing technologies enable the early detection of these threats, allowing for targeted interventions to protect crops.
Environmental impact assessment. It is used to monitor the effects of agricultural practices on the environment, including land degradation, deforestation, and changes in biodiversity. This helps in developing more sustainable farming practices.
Frost detection and weather anomalies. Remote sensing data, especially from thermal infrared sensors, can detect sudden temperature drops that may cause frost damage. Apple orchards in Washington State, for example, use UAV thermal imagery to detect microclimates and trigger frost protection systems.
Carbon sequestration and regenerative agriculture monitoring. Remote sensing is being used to quantify biomass and assess carbon storage in soil and vegetation. This supports carbon credit validation and is crucial in verifying regenerative practices like cover cropping, rotational grazing, and no-till farming.
How agricultural remote sensing turns reflectance into insight
Satellite imagery is more than an aerial photograph. Sensors measure how sunlight is reflected by crops across visible and non-visible wavelengths. Healthy plants absorb part of this energy for photosynthesis and reflect other wavelengths differently from plants experiencing stress. Mathematical formulas then convert those spectral differences into vegetation indices and visual maps.
“The sensors are so sensitive that they can capture these small differences,” explained Yevhenii Marchenko. The green, yellow, and red zones shown in a crop monitoring platform are therefore interpretations of measured reflectance—not direct diagnoses. They help users identify spatial variation and changes over time that deserve attention.
Because satellite data can be collected repeatedly throughout the growing season, farmers and agronomists can monitor current crop development and revisit historical imagery after harvest. This longer view is useful for distinguishing a one-season anomaly from a repeatedly underperforming area of the field.
NDVI, NDRE, and MSAVI: choosing the right vegetation index
No single vegetation index is optimal for every crop or growth stage. Marchenko highlighted several commonly used indices in remote sensing for agriculture:
- MSAVI (Modified Soil Adjusted Vegetation Index) is particularly useful early in the season, when seedlings cover only part of the field and exposed soil may distort the signal. It can reveal uneven emergence and low-vegetation zones more clearly than NDVI at this stage.
- NDVI (Normalized Difference Vegetation Index) is the most widely used option for monitoring vegetation vigor through much of the growing season. It helps compare crop development across a field and track changes over time.
- NDRE (Normalized Difference Red Edge Index) becomes valuable later in the season and for crops with dense canopies, such as corn, sunflower, and sugarcane. When NDVI begins to saturate, NDRE can capture subtler differences in chlorophyll and nutrient status.
- Chlorophyll-related indices can add another layer when the goal is to examine plant chlorophyll content or possible nutrient-related variation.
The practical lesson is to select an index according to the crop, canopy density, growth stage, and decision being made—not simply because it is available in the software.
Practical applications of GIS in agriculture
Bayer Crop Science employs Google Cloud for the analysis of billions of acres of terrain to gain deeper insights into the soil properties vital for our food crops’ growth. Utilizing a range of services provided by Google Cloud, Bayer’s data science teams are able to import, preserve, examine, and display geospatial information, crafting distinctive business perspectives.
Deere & Company uses Geographic Information Systems (GIS) and remote sensing to forge advancements in precision farming, aiding agriculturalists in enhancing crop production while minimizing ecological footprints. Notably, Deere’s platform, the John Deere Operations Center, integrates satellite data and various analytics to furnish agriculturists with insights into their fields, including data on soil hydration, plant vitality, and equipment efficiency.
Corteva Agriscience leverages GIS and remote sensing technologies to innovate and offer new solutions aimed at enhancing farm productivity and crop protection. A prime example of their technological application is the Enlist Weed Control system. This system employs satellite imagery along with various data points, enabling farmers to detect and effectively manage weed infestations.
Who benefits most from remote sensing in agriculture?
Remote sensing technology can be applied across crops and regions, but its value depends on scale, field accessibility, staffing, and the decision it supports. Marchenko noted that it is especially useful where physical scouting is difficult—for example, in mature sugarcane fields or orchards—and where an operation needs a fast overview before sending an agronomist or drone to a specific location.
The economics are often clearest for large farms and agribusinesses. Across thousands of hectares, even a small improvement in margin or a faster response to an emerging problem can produce a meaningful return. Satellite-based crop classification and yield estimation can also support food companies, insurers, and commodity businesses that need regional information about what is being grown, where it is located, and what the likely production potential may be.
For an individual smallholder, however, a standalone remote sensing platform may offer less value if the entire holding can be inspected directly or no one is available to interpret the data. Marchenko identified the lack of qualified staff and the need for immediate, practical recommendations as important adoption barriers. A farmer rarely needs another map; the farmer needs to know which field to inspect, what may require attention, and what to do next.
The most realistic adoption path is therefore incremental: begin with a clear problem and a familiar index such as NDVI, connect the imagery to existing farm records, and provide agronomic or technical support while users learn how the digital pattern corresponds to field reality.
Combining GIS, remote sensing, farm data, and AI
The next stage of agricultural remote sensing is not simply producing more imagery. It is integrating satellite data with weather records, IoT sensors, drone imagery, soil tests, machinery data, spraying maps, yield maps, and farm management software. Together, these layers can support crop detection, yield prediction, risk monitoring, field prioritization, and more context-aware recommendations.
Kovalchuk argued that satellite imagery should be treated as a structured historical data source rather than only as a current map. Comparing several seasons of vegetation indices with yield, soil, and application data can reveal relationships that no single layer shows on its own. AI can help digest these datasets, rank anomalies, and translate them into a more usable workflow for farmers and agronomists.
Marchenko expects AI to help move crop monitoring platforms from displaying data toward suggesting the next step—for example, identifying which field should be checked first or where irrigation may be needed. Novák nevertheless emphasized that these systems should act as an advising partner to a qualified agronomist, not a replacement. Their value lies in reducing repetitive monitoring and directing human expertise toward higher-value investigation and decisions.
Why ground truth remains essential
AI and remote sensing models still depend on reliable observations from the field. For disease-risk modeling, developers need records of where and when a disease occurred, what disease was present, and the surrounding conditions. Yield-estimation and crop-classification models likewise require local data for training, testing, and calibration.
“Ground data is essential, and it’s an integral part of remote sensing,” Marchenko said. Even models trained over many years and across multiple regions must be checked against local conditions. For users, the same principle applies: compare the platform with the field, learn what its patterns mean in local agronomic conditions, and calibrate decisions accordingly.
The future of remote sensing and GIS in agriculture is therefore best understood as a connected decision-support system: satellites provide consistent coverage, software organizes and analyzes multiple data layers, AI helps prioritize information, and agronomists validate what is happening on the ground.
Having troubles with remote sensing project?
FAQ
1. What is GIS, and how is it used in agriculture?
2. How does remote sensing benefit agriculture?
3. Can GIS and remote sensing technologies help in water management?
4. What are the environmental benefits of using GIS and remote sensing in farming?
GIS and remote sensing support sustainable land management practices, help monitor and combat the effects of climate change on agriculture, and contribute to preserving biodiversity and soil health.
Leave a comment