Detecting Potato Blight Weeks Early: What NDVI Drone Monitoring Reveals that RGB cannot

A 9-week field monitoring case using drone-acquired NDVI imagery, and what it means for trial design, early intervention and crop protection decision-making.

What the human eye misses

Standard RGB drone imagery captures what you would see from the air with your own eyes: color, texture, and visible damage. For many applications, that is sufficient. For early disease detection in agricultural field trials, it is not.

Vegetation indices such as NDVI (Normalized Difference Vegetation Index) work differently. Rather than looking at the combined wavelength, which gives you the same visible impression a normal RGB picture does, we look at the relationships between reflected light at different wavelengths, both visible and non-visible. NDVI looks at the relationship between reflected red light and near-infrared light. If there is low reflected light in the red band and high reflected light in the near-infrared, it can explain how effective photosynthesis is in the plant. This difference becomes measurable, mappable, and actionable in NDVI output, even when it is completely invisible in standard imagery.

The practical result is significant. NDVI can reveal physiological stress in crops before any visible symptom appears. For fungal diseases such as Phytophthora infestans, the pathogen responsible for potato blight, this detection window can open several weeks ahead of what RGB imagery or direct field observation would show.

NDVI can detect physiological stress in potato crops several weeks before symptoms become visible to the naked eye or in standard RGB imagery.

Nine weeks of Potato Blight development: What the data shows

In this monitoring series, drone flights covered a potato trial field at regular intervals across nine weeks. Each flight captured both standard RGB and multispectral imagery processed to NDVI output. The two datasets were then aligned and compared week by week.

In the early weeks, RGB imagery showed a uniform, apparently healthy crop. The NDVI output told a different story. Early patches of reduced reflectance appeared in areas that showed no visible symptom at all. These patches aligned precisely with areas where blight symptoms became visually apparent one to two weeks later.

By the time RGB imagery clearly indicated disease pressure, the NDVI data had already mapped the infection pattern weeks earlier. The spatial distribution, the rate of spread, and the most affected areas were all visible in the NDVI record long before standard imagery caught up.

Why Early Detection Matters for Field Trials

For crop protection field trials, accurate early disease detection is not merely useful. It is structurally important.

Trial protocols under EPPO guidelines require consistent, well-documented assessment of disease development across trial sites. Delayed detection compresses the observable window of disease progression. It reduces the statistical resolution of efficacy assessments. In some cases, a critical treatment timing gets missed entirely.

NDVI-based drone monitoring addresses each of these problems directly. By establishing a baseline early in the season and tracking deviation from that baseline week by week, teams can detect disease onset at a spatial and temporal resolution that ground-based scouting cannot reliably achieve. This is especially true across larger trial areas or multi-site programs.

What This Means for Intervention Timing

Beyond the trial context, the same capability applies directly to commercial crop protection decisions. Early NDVI signals identify which parts of a field are under stress and how rapidly that stress is spreading. This allows growers and agronomists to assess whether intervention is warranted before economic damage has occurred. That is a meaningful operational advantage in any crop protection program.

The Role of NDVI Field Trial Monitoring in Modern Trial Programs

Integrating multispectral drone monitoring into field trial design is not yet standard practice across the industry. At Agrolab, it forms part of how we approach trial execution where early disease detection, spatial variability analysis, or longitudinal crop health monitoring adds value to the data package.

The 9-week potato blight monitoring series presented here was part of our ongoing Research & Development at Agrolab. The full dataset, including raw NDVI values, flight parameters, and week-by-week comparative imagery, is available for discussion with clients and collaborators working on crop protection trial programs in the EU North Zone.

To discuss how drone-based NDVI monitoring could support your trial program, contact Martin Gejl, Innovation Manager at Agrolab: mg@agrolab.dk

Explore other posts

Northern Zone Efficacy Guidance 2025 (Version 10) – Key Updates

When applying for authorization of a plant protection product (PPP) in the EU Northern Zone, applicants must follow strict efficacy trial requirements. A newly updated Version 10.0 (2025) has now been released. Learn updated PPP trial requirements to streamline EU registration. This guidance defines […]

LEARN MORE

Agrolab's Drone Technology gets GEP-Approved for Field Trials

We are proud to announce that our innovative drone-based canopy height measurement method is now officially approved by the Danish GEP inspection unit. This technology aligns with EPPO guideline PP1/333(1), which supports the adoption of digital innovations for efficacy evaluations in plant protection...

LEARN MORE

Indlægget Detecting Potato Blight Weeks Early: What NDVI Drone Monitoring Reveals That RGB Cannot blev først udgivet på Agrolab.

Agrolab's Drone Technology gets GEP-Approved for Field Trials

How Drone Technology Transforms Field Trials

Our newly adopted drone technology overcomes these challenges by capturing thousands of data points per plot. Here’s how it works:

• Precision Data Collection: Drones measure canopy height across the entire plot, generating a true average without human bias.

• Advanced Segmentation: For early-stage crops, the technology identifies and isolates plant data, excluding soil measurements for enhanced accuracy.

• Increased Efficiency: Drones significantly reduce the time and labor required for data collection while improving overall data quality.

The result? More reliable and comprehensive insights into crop performance, empowering our clients to make informed decisions.

Figure 10: Orthophoto of trial. Purple dots points used for interpolating of ground elevation model. Green squares area used for height measurements.

Figure 11: Height model

Indlægget blev først udgivet på Agrolab.

Background: Image technology and drones can provide high-resolution pictures and assessments of all plots in a trial, a feature that is difficult when standing on the ground conducting visual assessments. Digital imaging is especially useful for assessing products that change crop color, cause desiccation, greening, crop stand changes etc.

Plant protection product development and registration requires detailed information on the products dose-response relation. The objective of this posting is to introduce the possibility of getting valuable data from a small trial with 3 replicates using drone images and logarithmic sprayers.

Methodology: The drone image and figure 1 below show the results from a cycloxydim application to a spring barley crop. We applied two formulations of cycloxydim. The application was made at BBCH 24 on the 23^rd of June 2022. The trial was made with 3 replicates, and the drone images were taken 28 days after application. The methodology of the logarithmic sprayer is to start with an initial high dose of 400 g cycloxydim/ha and to decrease subsequent doses in a logarithmic manner, ending with a final application of close to zero g/ha.

We used the open-source program R to analyze the trial. To extract the data from the images, we used FieldImageR (https://github.com/OpenDroneMap/FIELDimageR) which is developed for analyzing drone images of field trials. For the statistical modeling of the dose-response curves, we have used the R package DRC (https://cran.r-project.org/web/packages/drc/index.html) (see the also (https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0146021).

Each plot in the trial was divided into 50 subplots which have a length of 40 cm, and the center dose of each plot was calculated. The first 80 cm and the last 80 cm were not included in the calculation to avoid the effect of border spraying. This gave 46 doses to model the dose-response curves. The number of doses you can retrieve of such an Image is shown in Figure 2.

With a normal RGB image you can calculate different vegetation indexes. We used the index Excess Green, which is 2 * Green band – red band – blue band. Numerous other indexes can be calculated from the RGB bands, and even more indexes are possible if you have infrared.

Given that the two treatments we compared are the same active, just different formulations, we will assume that the products have the same upper and lower limit. The data indicates there could be hormesis (a small amount of the active gives a positive plant growth) which is not uncommon for herbicides, and the DRC package allows you to model the dose-response curve both with and without hormesis (se figure 3).

Results and Conclusion: With the program, it is possible to calculate different ED_x (effective dose) values. We calculated the values and presented them with a 95% confidence interval. In table 1 you can see the ED₅₀ values estimated for the dose-response curves with and without hormesis.

The advantage of using logarithmic trials for analyzing dose-response relations is obvious. In a plot where we sprayed 60 m², we get an unlimited number of doses. If this had been done with a normal randomized block design, we would have needed at least 6 well-chosen doses to model the curve, and this would require larger trials and would be more time consuming. With the logarithmic trial, you only need to choose a starting dose where you are confident that you get almost 100% efficacy. Following the analyses of the dose-response curves, you can determine which doses are interesting for future investigation.

If you would like to learn more about Agrolab’s digital imaging solutions, please contact Martin Gejl (Email: mg@agrolab.dk; or Mobile +45 20736575).

Indlægget Logarithmic trial designs: A useful tool blev først udgivet på Agrolab.