The Technological Shift Toward Smarter Vegetation Analysis
Computer science might not be the first thing that comes to mind when you think about farming, but a growing field of environmental technologists is changing that. Regenerative agriculture, a farming approach with a focus on building and maintaining soil health, is gaining traction as a solution for the improvement of soil health, biodiversity, and climate change. Tools that analyze crop and soil health by use of satellite data for remote sensing and indexes such as the Normalized Difference Vegetation Index are being used to give farmers deeper insights into their land. This article aims to explore these technologies and faring approaches that are driving this transformation.
If you haven’t heard of regenerative agriculture before, it is the practice of restoring degraded soil health and ecosystems while enhancing farm profitability. The practice isn’t just for crop farms, but animal farms too. This can be done using farm management practices such as, but not limited to, crop or grazing rotation, no-till planting, and lessening the use of pesticides. You might ask what soil health is related to farming and climate? The World Economic Forum states that, “when soil is healthy, it produces more food and nutrition, stores more carbon and increases biodiversity – the variety of species” (Masterson, 2022). This isn’t something new. Arohi Sharma, a water and agriculture policy analyst at NRDC, has stated, “the regenerative agriculture movement is the dawning realization among more people that an Indigenous approach to agriculture can help restore ecologies, fight climate change, rebuild relationships, spark economic development, and bring joy” (NRDC, 2021). Modern agriculture still faces serious challenges, most notably widespread soil degradation (the decline in soil quality), nutrient depletion, and lack of actionable feedback for farmers.
This is where environmental technologists enter the conversation. Their tools and solutions offer farmers the ability to analyze, predict, and respond to soil health and environmental conditions in real time. One of these tools involves satellite data gathered by remote sensing techniques. A program titled the Landsat program managed by NASA and the U.S. Geological Survey since 1972 has been collecting and tracking “land use and to document land change due to climate change, urbanization, drought, wildfire, biomass changes (carbon assessments), and a host of other natural and human – caused changes” (USGS, 2024).
Using Landsat satellite imagery, a tool called the Normalized Difference Vegetation Index (NDVI) can be calculated to measure plant “greenness” or health compared to bare soils. NDVI has also “been used to estimate the cumulative effective of rainfall on vegetation over a certain time period, rangeland carrying capacity, crop yields for different crop types, and the quality of the environment as habitat for various animals, pests and diseases” (International Production Assessment Division, n.d.). This remote sensing method works by measuring “the difference between visible and near-infrared reflectance of the vegetation (Agrio, 2023). This depends on “leaf area, chlorophyll content, age of leaves, canopy density, and soil type” (Agrio, 2023).
NDVI = (NIR-Red) / NIR + Red)
The equation above shows how NDVI is calculated. NIR stands for near-infrared light, and Red is the visible red light. Healthy vegetation absorbs red light and reflects near-infrared light. Unhealthy or sparse vegetation reflects both similarly, resulting in a lower NDVI score. The scores or outcome values range from -1 to 1. Sand, rock, or snow show values of 0.1 or less, sparse vegetation leads to moderate values between 0.2 to 0.5, and dense vegetation shows values of 0.6 to 0.9. A high NDVI (closer to +1) tells us that the area is densely populated, crops are healthy, and have high chlorophyll content. A low NDVI score (closer to 0 or negative) tells us that the land is bare, and crops are stressed.
NDVI with class range in ArcGIS: GIS & RS Solution YouTube
An NDVI map can be created using these values, which can be seen above. Maps like these can reveal information about the land, such as crop stress due to drought, pests, or disease before it’s visible, variability in yield potential across a field, success of regenerative techniques, and or erosion-prone or underperforming areas that may need attention. Agrio, a software application that allows farmers to monitor their fields without requiring prior knowledge. The farmer would draw their field onto the map to allow the application to show “different stages of plant development in the various fields, and internal variation inside individual fields” (Agrio, 2023). With information like this, the maps guide decisions on irrigation, fertilization, and regenerative practices before problems appear to the naked eye.
This doesn’t come without its limitations. Fractional vegetation coverage (FVC) is the proportion of surface area that is covered by green vegetation. As discussed above, NDVI is used to analyze green biomass, essentially estimating FVC. A paper titled “A comparative study on the applicability and effectiveness of NSVI and NDVI for estimating fractional vegetation cover based on multi-source remote sensing image” discusses how “NDVI can be oversaturated and easily affected by problems such as ‘shadow’ in images, which leads to a decrease in the precision of FVC estimation” (Xu et al., 2023). Here, research discussed how the Normalized Shaded Vegetation Index (NSVI) may be a better alternative to NDVI.
The study gathered satellite imagery coming from Sentinel-2, Landsat, and other high-resolution earth observation systems. Because of the oversaturation issue due to vegetation cover and susceptibility to shadows in images, “Xu et al. established the Shaded Vegetation Index (SVI) from the spectral difference between vegetation and other features in shaded areas of mountain hills and further constructed the Normalized Shaded Vegetation Index” (Xu et al., 2023). This index aims to resolve the issues that face NDVI, improving the accuracy of FVC. The formulas below show how SVI and NSVI are calculated. SVImax is the maximum value of SVI, whereas SVI min is the minimum value of SVI.
SVI = NIR * (NIR-Red) / NIR + Red)
NSVI = (SVI - SVImin) / (SVImax - SVImin)
The results of the study found that “compared to NDVI, NSVI-based thresholding can effectively distinguish shaded areas of different brightness and the FVC estimation is more stable and better in high-brightness shaded areas” (Xu et al., 2023). They further noted that “the estimation accuracy of FVC based on NSVI is slightly higher than that of NDVI in medium-high-rank and high-rank FVC areas in bright areas, and the error is more stable” (Xu et al., 2023). Medium-high-rank and high-rank FVC refers to the percentage of vegetation cover.
It should be noted that “NSVI was proposed mainly for mountains and hills, and did not consider non-forested areas” (Xu et al., 2023). This doesn’t necessarily mean that NSVI isn’t useful for agriculture in the U.S. The ability to correct for soil and illumination effects does suggest potential applications for regenerative agriculture. Farms practicing regenerative methods often have mixed or uneven distribution of plants with varying canopy heights and exposed soil patches, which may lead to less accurate NDVI results compared to NSVI.
This tells us that for most conventional U.S. farms that include big fields and dense crops, NDVI would be sufficient and effective. However, since we are talking about regenerative agriculture practices such as diverse cropping, cover cropping, no-till farming, and or dealing with patchy vegetation, NSVI would provide more accurate and reliable vegetation monitoring. In my next article, I will be discussing yet another technique for farmers to monitor crops, specifically IoT sensor-based networks for real-time monitoring and the technology behind them. Remote sensing techniques for monitoring the health of fields are useful but represent just one piece of the larger collection of technological solutions that is emerging to support regenerative farming.
Works Cited
Masterson, Victoria. “What Is Regenerative Agriculture?” World Economic Forum, Forum Stories, 11 Oct. 2022, www.weforum.org/stories/2022/10/what-is-regenerative-agriculture/.
“NDVI with Class Range in ArcGIS.” YouTube, YouTube, 2022, www.youtube.com/watch?v=ssxnVGFPbrg.
“Normalized Difference Vegetation Index (NDVI).” International Production Assessment Division (IPAD) - Home Page, ipad.fas.usda.gov/cropexplorer/Definitions/spotveg.htm. Accessed 29 Apr. 2025.
“Regenerative Agriculture 101.” NRDC, NRDC, 29 Nov. 2021, www.nrdc.org/stories/regenerative-agriculture-101.
“What Is the Landsat Satellite Program and Why Is It Important?” USGS, USGS, 28 June 2024, www.usgs.gov/faqs/what-landsat-satellite-program-and-why-it-important.
“What You Should Know about Monitoring Ndvi in Agriculture.” Agrio, 17 Sept. 2023, agrio.app/What-you-should-know-about-monitoring-NDVI-imagery/.
Xu, Zhang-hua, et al. “Full Article: A Comparative Study on the Applicability and Effectiveness of NSVI and NDVI for Estimating Fractional Vegetation Cover Based on Multi-Source Remote Sensing Image.” Taylor & Francis Online, 15 Mar. 2023, www.tandfonline.com/doi/full/10.1080/10106049.2023.2184501.
