Verifying Crop Loss from Space: Satellite Remote Sensing as an Evidentiary Standard in Crop Insurance Indemnity Adjustment

Loss verification is the operational bottleneck of crop insurance: an indemnity can only be paid if the shortfall between the guaranteed yield and the actual yield can be demonstrated over the whole insured area, yet conventional loss adjustment rests on small, non-probabilistic field samples taken, at best, a few days before harvest. This paper examines whether satellite remote sensing can supply the missing evidence. Combining a doctrinal-normative analysis of the principle of indemnity, utmost good faith and fair claims handling with a methodological review of the remote-sensing yield-estimation literature, the study subjects satellite-based verification to a three-layered test: technical validity, evidentiary weight, and conformity with the indemnity principle and fair claims handling. The review shows that biophysical indicators reconstructed from multi-temporal Sentinel-2 and Landsat imagery — normalised difference vegetation index (NDVI), enhanced vegetation index (EVI) and kernel variants such as kNDVI — recover a substantial share of out-of-sample yield variability (external validation coefficients of determination of 0.77–0.86 for wheat and barley; relative errors near 7–8% for within-field forecasting), and that continuous whole-area coverage removes the extrapolation fallacy at the root of conventional under-indemnity. The paper argues that estimated-yield-per-plot benchmarks against an official reference productivity constitute probative evidence, provided the source is independent, the data are replicable, the algorithm is transparent and the finding converges with other evidence; it proposes a ten-principle good-practice framework for satellite-assisted loss adjustment. The contribution is a normative-technical architecture that regulators can accredit and adjudicators can weigh. crop insurance; remote sensing; loss adjustment; NDVI; evidentiary standard; indemnity principle

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-12
DOI
https://doi.org/10.5281/zenodo.24170360
Primary Topic
Remote Sensing in Agriculture
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Verifying Crop Loss from Space: Satellite Remote Sensing as an Evidentiary Standard in Crop Insurance Indemnity Adjustment

Mark Giuliani Krás Borges
Zenodo (CERN European Organization for Nuclear Research)
Remote Sensing in Agriculture
article

Verifying Crop Loss from Space: Satellite Remote Sensing as an Evidentiary Standard in Crop Insurance Indemnity Adjustment

Mark Giuliani Krás Borges
article en

Abstract

Loss verification is the operational bottleneck of crop insurance: an indemnity can only be paid if the shortfall between the guaranteed yield and the actual yield can be demonstrated over the whole insured area, yet conventional loss adjustment rests on small, non-probabilistic field samples taken, at best, a few days before harvest. This paper examines whether satellite remote sensing can supply the missing evidence. Combining a doctrinal-normative analysis of the principle of indemnity, utmost good faith and fair claims handling with a methodological review of the remote-sensing yield-estimation literature, the study subjects satellite-based verification to a three-layered test: technical validity, evidentiary weight, and conformity with the indemnity principle and fair claims handling. The review shows that biophysical indicators reconstructed from multi-temporal Sentinel-2 and Landsat imagery — normalised difference vegetation index (NDVI), enhanced vegetation index (EVI) and kernel variants such as kNDVI — recover a substantial share of out-of-sample yield variability (external validation coefficients of determination of 0.77–0.86 for wheat and barley; relative errors near 7–8% for within-field forecasting), and that continuous whole-area coverage removes the extrapolation fallacy at the root of conventional under-indemnity. The paper argues that estimated-yield-per-plot benchmarks against an official reference productivity constitute probative evidence, provided the source is independent, the data are replicable, the algorithm is transparent and the finding converges with other evidence; it proposes a ten-principle good-practice framework for satellite-assisted loss adjustment. The contribution is a normative-technical architecture that regulators can accredit and adjudicators can weigh. crop insurance; remote sensing; loss adjustment; NDVI; evidentiary standard; indemnity principle

Zenodo (CERN European Organization for Nuclear Research)
Zero hunger
Remote Sensing in Agriculture
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon