Sight for Sorghums: Comparisons of Satellite- and Ground-Based Sorghum Yield Estimates in Mali

Abstract

The advent of multiple satellite systems capable of resolving smallholder agricultural plots raises possibilities for significant advances in measuring and understanding agricultural productivity in smallholder systems. However, since only imperfect yield data are typically available for model training and validation, assessing the accuracy of satellite-based estimates remains a central challenge. Leveraging a survey experiment in Mali, this study uses plot-level sorghum yield estimates, based on farmer reporting and crop cutting, to construct and evaluate estimates from three satellite-based sensors. Consistent with prior work, the analysis indicates low correlation between the ground-based yield measures (r = 0.33). Satellite greenness, as measured by the growing season peak value of the green chlorophyll vegetation index from Sentinel-2, correlates much more strongly with crop cut (r = 0.48) than with self-reported (r = 0.22) yields. Given the inevitable limitations of ground-based measures, the paper reports the results from the regressions of self-reported, crop cut, and (crop cut-calibrated) satellite sorghum yields. The regression covariates explain more than twice as much variation in calibrated satellite yields (R2 = 0.25) compared to self-reported or crop cut yields, suggesting that a satellite-based approach anchored in crop cuts can be used to track sorghum yields as well or perhaps better than traditional measures. Finally, the paper gauges the sensitivity of yield predictions to the use of Sentinel-2 versus higher-resolution imagery from Planetscope and DigitalGlobe. All three sensors exhibit similar performance, suggesting little gains from finer resolutions in this system.

High-Throughput Estimation of Crop Traits: A Review of Ground and Aerial Phenotyping Platforms

“…Finally, micro/nanosatellites can provide data in several spectral bands (which are sensitive to the crop structure, leaf pigment, and water content), and they enable meter-levelresolution images for estimating crop phenotyping traits at a very large scale [24], [79], [87], [88], [144], [193], [236], [239]. Micro/nanosatellites include optical and synthetic aperture radar (SAR) satellites.…”

Trunk Model Establishment and Parameter Estimation for a Single Tree Using Multistation Terrestrial Laser Scanning

“…However, hyperspectral and infrared are more suitable for stand biomass, chlorophyll index [19] [20], pest and disease monitoring [21], etc. UAV images or satellite highprecision images are suitable for biomass of forest stands and tend to check large areas of resources [22].…”

Understanding the Requirements for Surveys to Support Satellite-Based Crop Type Mapping: Evidence from Sub-Saharan Africa

“…With the commencement of the European Space Agency's Sentinel-2 mission in 2015 and the subsequent surge in the public availability of high-resolution satellite imagery, research has shown the feasibility of satellite-based monitoring of agricultural outcomes in smallholder farming systems (Becker-Reshef et al, 2020;Burke and Lobell, 2017;Jin et al, 2017Jin et al, , 2019Lambert et al, 2018;Lobell et al, 2019Lobell et al, , 2020. Latest advances in satellite imagery and remote sensing techniques have the potential to provide timely insights into conditions on the ground and can fill gaps in agricultural monitoring and statistics (Nakalembe, 2020).…”

“…Satellite-based approaches to mapping agricultural outcomes, such as crop-specific estimates of cultivated areas and yields, require data for training and validating the underlying remote sensing models. The quality and spatial resolution of satellite-based estimates is directly impacted by the data used for model training and validation (Lobell et al, 2019(Lobell et al, , 2020. Recent earth observation research that has focused on low-income countries has relied largely on two sources of training and validation data: (i) manually-labeled optical imagery (DeFourny et al, 2019;Xiong et al, 2017;Wei et al, 2020), 2 and (ii) ground data collection, including as part of household and farm surveys (Hegarty-Craver et al, 2020;Jin et al, 2017Jin et al, , 2019Kerner et al, 2020;Lambert et al, 2018;Richard et al, 2017).…”