Wheat Yield Estimation at High Spatial Resolution through the Assimilation of Sentinel-2 Data into a Crop Growth Model

Abstract

Monitoring crop growth and estimating crop yield are essential for managing agricultural production, ensuring food security, and maintaining sustainable agricultural development. Combining the mechanistic framework of a crop growth model with remote sensing observations can provide a means of generating realistic and spatially detailed crop growth information that can facilitate accurate crop yield estimates at different scales. The main objective of this study was to develop a robust estimation methodology of within-field winter wheat yield at a high spatial resolution (20 m × 20 m) by combining a light use efficiency-based model and Sentinel-2 data. For this purpose, Sentinel-2 derived leaf area index (LAI) time series were assimilated into the Simple Algorithm for Yield Estimation (SAFY) model using an ensemble Kalman filter (EnKF). The study was conducted on rainfed winter wheat fields in southern Sweden. LAI was estimated using vegetation indices (VIs) derived from Sentinel-2 data with semi-empirical models. The enhanced two-band vegetation index (EVI2) was found to be a useful VI for LAI estimation, with a coefficient of determination (R2) and a root mean square error (RMSE) of 0.80 and 0.65 m2/m2, respectively. Our findings demonstrate that the assimilation of LAI derived from Sentinel-2 into the SAFY model using EnKF enhances the estimation of within-field spatial variability of winter wheat yield by 70% compared to the baseline simulation without the assimilation of remotely sensed data. Additionally, the assimilation of LAI improves the accuracy of winter wheat yield estimation by decreasing the RMSE by 53%. This study demonstrates an approach towards practical applications of freely accessible Sentinel-2 data and a crop growth model through data assimilation for fine-scale mapping of crop yield. Such information is critical for quantifying the yield gap at the field scale, and to aid the optimization of management practices to increase crop production.

Optimizing Crop Yield Estimation through Geospatial Technology: A Comparative Analysis of a Semi-Physical Model, Crop Simulation, and Machine Learning Algorithms

“…ngineering 2024, 6,45 The GP-level yield in Bareilly district exhibited a range from 2111 kg/ha to 4628 kg a variation that was determined through the implementation of the DSSAT model (Fig 7). The model was executed by stratifying areas based on similarities in soil type, wea conditions and cultivation practices.…”

“…Many studies have attempted to utilize this strategy of combining crop modelling and remote sensing [34,35]. Past research studies on wheat yield estimation have combined remote sensing with various crop models [36], including WOFOST [37,38], CERES-Wheat [39][40][41], Decision Support System for Agrotechnology Transfer (DSSAT) [42], APSIM, INFOCROP [43], STICS [44], SAFY [45], Wheat-Grow [46], etc.…”

Modeling Plant Height and Biomass Production of Cluster Bean and Sesbania across Diverse Irrigation Qualities in Pakistan’s Thar Desert

“…There are several growth prediction models that have been developed by using plant height to predict biomass production by using artificial neural network and multiple linear regression techniques [25,26]. A simulation growth model should be based on the biological and physiological parameters measured in real plants [27,28]. Plant species growth models and estimation techniques are the main methods to explore these problems [29][30][31][32].…”

Yield Estimation of Wheat Using Cropland Masks from European Common Agrarian Policy: Comparing the Performance of EVI2, NDVI, and MTCI in Spanish NUTS-2 Regions

“…The number of studies that use other VIs, such as EVI2 and MTCI, is lower. EVI2 is used by [1] in the region of Punjab and Haryana in India, and MTCI by [11] in South Dakota, USA, [41] in Henan Province, China, [42] in Southern Sweden, and [43] in Iran. Selecting a VI during the process of modeling wheat production and yield may impact the models' performance.…”