Preprints
https://doi.org/10.5194/hess-2021-600
https://doi.org/10.5194/hess-2021-600

  24 Nov 2021

24 Nov 2021

Review status: this preprint is currently under review for the journal HESS.

Machine-learning approach to crop yield prediction with the spatial extent of drought

Vitali Diaz1,2, Ahmed A. A. Osman3, Gerald A. Corzo Perez1,2, Henny A. J. Van Lanen4, Shreedhar Maskey2, and Dimitri Solomatine1,2,5 Vitali Diaz et al.
  • 1IHE Delft Institute for Water Education, Hydroinformatics Chair group, Delft, 2601 DA, the Netherlands
  • 2Delft University of Technology, Delft, the Netherlands
  • 3Arcadis, Wales, United Kingdom
  • 4Hydrology and Quantitative Water Management Group, Wageningen University, Wageningen, the Netherlands
  • 5Water Problems Institute of the Russian Academy of Sciences, Moscow, Russia

Abstract. Crop yield is one of the variables used to assess the impact of droughts on agriculture. Crop growth models calculate yield and variables related to plant development and become more suitable for crop yield estimation. However, these models are limited in that specific data are needed for computation. Given this limitation, machine learning (ML) models are often widely utilised instead, but their use with the spatial characteristics of droughts as input data is limited. This research explored the spatial extent of drought (area) as input data for building an approach to predict seasonal crop yield. This ML approach is made up of two components. The first includes polynomial regression (PR) models, and the second considers artificial neural network (ANN) models. In this approach, the purpose was to evaluate both types of ML models (PR and ANN) and integrate them into one operational tool. The logic is as follows: ANN models determine the most accurate predictions, but in practice, issues regarding data retrieval and processing can make the use of equations, i.e. PR, preferable. The proposed approach provides these PR equations to perform such calculations with early and preliminary input. The estimates can be further improved when the ANN models are run with the final input data. The results indicated that the empirical equations (PR) produced good predictions when using drought area as the input. ANN provides better estimates, in general. This research will improve drought monitoring systems for assessing drought effects. Since it is currently possible to calculate drought areas within these systems, the direct application of the prediction of drought effects is possible to integrate by following approaches such as the one presented or similar.

Vitali Diaz et al.

Status: open (until 19 Jan 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Vitali Diaz et al.

Vitali Diaz et al.

Viewed

Total article views: 326 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
262 63 1 326 0 2
  • HTML: 262
  • PDF: 63
  • XML: 1
  • Total: 326
  • BibTeX: 0
  • EndNote: 2
Views and downloads (calculated since 24 Nov 2021)
Cumulative views and downloads (calculated since 24 Nov 2021)

Viewed (geographical distribution)

Total article views: 318 (including HTML, PDF, and XML) Thereof 318 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 01 Dec 2021
Download
Short summary
Drought effects on crops are usually evaluated through crop yield (CY). The hypothesis is that the drought spatial extent is a good input to predict CY. A machine learning approach to predict crop yield is introduced. The use of drought area was found suitable. Since it is currently possible to calculate drought areas within drought monitoring systems, the direct application to predict drought effects can be integrated into them by following approaches such as the one presented or similar.