Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Regional-Scale Cotton Yield Estimate in the Brazilian Cerrado Using Simple Linear Regression Models with Time-Series of Vegetation Indices from EOS-MODIS Satellite Data

Version 1 : Received: 23 February 2024 / Approved: 23 February 2024 / Online: 26 February 2024 (07:25:18 CET)

A peer-reviewed article of this Preprint also exists.

de Siqueira, D.A.B.; Vaz, C.M.P.; da Silva, F.S.; Ferreira, E.J.; Speranza, E.A.; Franchini, J.C.; Galbieri, R.; Belot, J.L.; de Souza, M.; Perina, F.J.; das Chagas, S. Estimating Cotton Yield in the Brazilian Cerrado Using Linear Regression Models from MODIS Vegetation Index Time Series. AgriEngineering 2024, 6, 947-961. de Siqueira, D.A.B.; Vaz, C.M.P.; da Silva, F.S.; Ferreira, E.J.; Speranza, E.A.; Franchini, J.C.; Galbieri, R.; Belot, J.L.; de Souza, M.; Perina, F.J.; das Chagas, S. Estimating Cotton Yield in the Brazilian Cerrado Using Linear Regression Models from MODIS Vegetation Index Time Series. AgriEngineering 2024, 6, 947-961.

Abstract

Crop yield estimation supported by satellite remote sensing data can provide expeditious and strategic information for farmers’ decision-making. Most recent forecasting methods have indicated a promising pathway based on machine learning algorithms. However, validation performances, demand for big data and their inherent inexplicability have not yet consolidated a substantial differential to replace methods based on simpler and more understandable models. This paper proposes an approach based on simple linear models fitted from vegetation indices (VIs) assessed at regular intervals of time series derived from MODIS satellite images, aiming to forecast cotton yields in representative areas of the Brazilian Cerrado. Data from 281 commercial production plots were taken to train (167 plots) and test (114 plots) linear regression models relating seed cotton yield and nine well-known VIs averaged in 15-days intervals. Among the evaluated VIs, EVI (Enhanced Vegetation Index) and TVI (Triangular Vegetation Index) showed the lowest root mean square errors (RMSE) and the highest determination coefficients. The best periods for in-season yield prediction were from the 90-105 to 135-150 days after sowing (DAS), i.e. phenological phases corresponding to boll development, open boll and fiber maturation, with lowest RMSE of about 750 kg ha-1 and R2=0.70. The best forecasts for early crop stages were provided by models at the peaks (maximum value of the VI time-series) for EVI and TVI, which occurred around 80-90 DAS. The proposed approach makes the yield predictability more inferable along the crop time series just by providing sowing dates, contour maps and its respective VIs.

Keywords

remote sensing; yield prediction; cotton; Brazilian Cerrado

Subject

Biology and Life Sciences, Agricultural Science and Agronomy

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.