<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Agricultural operators can predict the yield of wheat at different stages of growth, development, and harvesting and take different measures to realize precise management. The purpose of this paper is to apply agricultural mechanical engineering automation to wheat yield prediction, and a UAV multimodal data wheat yield prediction model is developed using the RMGF algorithm. Different data sources, such as vertical distribution of terrain and spatial variability, canopy height and wheat plant height, canopy temperature difference, vegetation spectral characteristics, and vegetation index, were extracted using an agricultural UAV. Then GF decomposition algorithm based on MSD decomposes the multimodal image into an approximate image and detail image, and after optimization of the fused weight map using RSA, the fused image is obtained by IMST according to the optimized weight map. The model was used to carry out regression analysis of yield prediction for three types of wheat, heat-tolerant, medium heat-tolerant, and high-temperature-sensitive, and finally predicted the wheat yield from 2015 to 2024 in a production area. It was found that the R² of the RMGF multimodal model in this paper predicted the three kinds of wheat yields as 0.7936, 0.8609, and 0.9262 with excellent accuracy results. The predicted yields were basically in line with the actual yields in the high-yield portion, with large prediction errors above 9000 kg/ha. The prediction error for wheat was within 0-2.26%, and the predicted yield in a main wheat production area was 7050 kg/ha in 2024. This study provides a feasible method for large-scale yield estimation in the main production area, which contributes to high-throughput plant phenotyping and agricultural precision reform.</p>
</abstract>

Agricultural operators can predict the yield of wheat at different stages of growth, development, and harvesting and take different measures to realize precise management. The purpose of this paper is to apply agricultural mechanical engineering automation to wheat yield prediction, and a UAV multimodal data wheat yield prediction model is developed using the RMGF algorithm. Different data sources, such as vertical distribution of terrain and spatial variability, canopy height and wheat plant height, canopy temperature difference, vegetation spectral characteristics, and vegetation index, were extracted using an agricultural UAV. Then GF decomposition algorithm based on MSD decomposes the multimodal image into an approximate image and detail image, and after optimization of the fused weight map using RSA, the fused image is obtained by IMST according to the optimized weight map. The model was used to carry out regression analysis of yield prediction for three types of wheat, heat-tolerant, medium heat-tolerant, and high-temperature-sensitive, and finally predicted the wheat yield from 2015 to 2024 in a production area. It was found that the R² of the RMGF multimodal model in this paper predicted the three kinds of wheat yields as 0.7936, 0.8609, and 0.9262 with excellent accuracy results. The predicted yields were basically in line with the actual yields in the high-yield portion, with large prediction errors above 9000 kg/ha. The prediction error for wheat was within 0-2.26%, and the predicted yield in a main wheat production area was 7050 kg/ha in 2024. This study provides a feasible method for large-scale yield estimation in the main production area, which contributes to high-throughput plant phenotyping and agricultural precision reform.

Research on the application method of agricultural machinery engineering automation based on multimodal characteristics

Beijing University of Civil Engineering and Architecture

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

Agricultural operators can predict the yield of wheat at different stages of growth, development, and harvesting and take different measures to realize precise...

Research on the application method of agricultural machinery engineering automation based on multimodal characteristics

Publicado en línea: 05 ago 2024

Páginas: -

Recibido: 17 abr 2024

Aceptado: 04 jul 2024

DOI: https://doi.org/10.2478/amns-2024-2137

Palabras clave
SVM classifier, MLR, Bootstrap filtering algorithm, Remote sensing data fusion, Yield prediction

© 2024 Xianggeng Wang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Research on the application method of agricultural machinery engineering automation based on multimodal characteristics

Publicado en línea: 05 ago 2024

Páginas: -

Recibido: 17 abr 2024

Aceptado: 04 jul 2024

DOI: https://doi.org/10.2478/amns-2024-2137

Palabras claveSVM classifier, MLR, Bootstrap filtering algorithm, Remote sensing data fusion, Yield prediction

© 2024 Xianggeng Wang et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Palabras clave
SVM classifier, MLR, Bootstrap filtering algorithm, Remote sensing data fusion, Yield prediction