Prediction of Winter Wheat Yield and Interpretable Accuracy Under Different Water and Nitrogen Treatments Based on CNNResNet-50
Winter wheat yield prediction is critical for optimizing field management plans and guiding agricultural production. To address the limitations of conventional manual yield estimation methods, including low efficiency and poor interpretability, this study innovatively proposes an intelligent yield e...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Agronomy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4395/15/7/1755 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839616715356372992 |
|---|---|
| author | Donglin Wang Yuhan Cheng Longfei Shi Huiqing Yin Guangguang Yang Shaobo Liu Qinge Dong Jiankun Ge |
| author_facet | Donglin Wang Yuhan Cheng Longfei Shi Huiqing Yin Guangguang Yang Shaobo Liu Qinge Dong Jiankun Ge |
| author_sort | Donglin Wang |
| collection | DOAJ |
| description | Winter wheat yield prediction is critical for optimizing field management plans and guiding agricultural production. To address the limitations of conventional manual yield estimation methods, including low efficiency and poor interpretability, this study innovatively proposes an intelligent yield estimation method based on a convolutional neural network (CNN). A comprehensive two-factor (fertilization × irrigation) controlled field experiment was designed to thoroughly validate the applicability and effectiveness of this method. The experimental design comprised two irrigation treatments, sufficient irrigation (C) at 750 m<sup>3</sup> ha<sup>−1</sup> and deficit irrigation (M) at 450 m<sup>3</sup> ha<sup>−1</sup>, along with five fertilization treatments (at a rate of 180 kg N ha<sup>−1</sup>): (1) organic fertilizer alone, (2) organic–inorganic fertilizer blend at a 7:3 ratio, (3) organic–inorganic fertilizer blend at a 3:7 ratio, (4) inorganic fertilizer alone, and (5) no fertilizer control. The experimental protocol employed a DJI M300 RTK unmanned aerial vehicle (UAV) equipped with a multispectral sensor to systematically acquire high-resolution growth imagery of winter wheat across critical phenological stages, from heading to maturity. The acquired multispectral imagery was meticulously annotated using the Labelme professional annotation tool to construct a comprehensive experimental dataset comprising over 2000 labeled images. These annotated data were subsequently employed to train an enhanced CNN model based on ResNet50 architecture, which achieved automated generation of panicle density maps and precise panicle counting, thereby realizing yield prediction. Field experimental results demonstrated significant yield variations among fertilization treatments under sufficient irrigation, with the 3:7 organic–inorganic blend achieving the highest actual yield (9363.38 ± 468.17 kg ha<sup>−1</sup>) significantly outperforming other treatments (<i>p</i> < 0.05), confirming the synergistic effects of optimized nitrogen and water management. The enhanced CNN model exhibited superior performance, with an average accuracy of 89.0–92.1%, representing a 3.0% improvement over YOLOv8. Notably, model accuracy showed significant correlation with yield levels (<i>p</i> < 0.05), suggesting more distinct panicle morphological features in high-yield plots that facilitated model identification. The CNN’s yield predictions demonstrated strong agreement with the measured values, maintaining mean relative errors below 10%. Particularly outstanding performance was observed for the organic fertilizer with full irrigation (5.5% error) and the 7:3 organic-inorganic blend with sufficient irrigation (8.0% error), indicating that the CNN network is more suitable for these management regimes. These findings provide a robust technical foundation for precision farming applications in winter wheat production. Future research will focus on integrating this technology into smart agricultural management systems to enable real-time, data-driven decision making at the farm scale. |
| format | Article |
| id | doaj-art-6c0e4ad6e5ad42d6afc280b92b10b58c |
| institution | Matheson Library |
| issn | 2073-4395 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Agronomy |
| spelling | doaj-art-6c0e4ad6e5ad42d6afc280b92b10b58c2025-07-25T13:10:21ZengMDPI AGAgronomy2073-43952025-07-01157175510.3390/agronomy15071755Prediction of Winter Wheat Yield and Interpretable Accuracy Under Different Water and Nitrogen Treatments Based on CNNResNet-50Donglin Wang0Yuhan Cheng1Longfei Shi2Huiqing Yin3Guangguang Yang4Shaobo Liu5Qinge Dong6Jiankun Ge7College of Water Conservancy, North China University of Water Resources and Electric Power, Zhengzhou 450045, ChinaCollege of Water Conservancy, North China University of Water Resources and Electric Power, Zhengzhou 450045, ChinaCollege of Water Conservancy, North China University of Water Resources and Electric Power, Zhengzhou 450045, ChinaCollege of Water Conservancy, North China University of Water Resources and Electric Power, Zhengzhou 450045, ChinaSchool of Computing, University of Portsmouth, Portsmouth PO1 3HE, UKSchool of Water Resources and Environment Engineering, Nanyang Normal University, Nanyang 473061, ChinaInstitute of Water-Saving Agriculture in Arid Areas of China (IWSA), Northwest A&F University, Yangling 712100, ChinaHenan Key Laboratory of Water-Saving Agriculture, Zhengzhou 450045, ChinaWinter wheat yield prediction is critical for optimizing field management plans and guiding agricultural production. To address the limitations of conventional manual yield estimation methods, including low efficiency and poor interpretability, this study innovatively proposes an intelligent yield estimation method based on a convolutional neural network (CNN). A comprehensive two-factor (fertilization × irrigation) controlled field experiment was designed to thoroughly validate the applicability and effectiveness of this method. The experimental design comprised two irrigation treatments, sufficient irrigation (C) at 750 m<sup>3</sup> ha<sup>−1</sup> and deficit irrigation (M) at 450 m<sup>3</sup> ha<sup>−1</sup>, along with five fertilization treatments (at a rate of 180 kg N ha<sup>−1</sup>): (1) organic fertilizer alone, (2) organic–inorganic fertilizer blend at a 7:3 ratio, (3) organic–inorganic fertilizer blend at a 3:7 ratio, (4) inorganic fertilizer alone, and (5) no fertilizer control. The experimental protocol employed a DJI M300 RTK unmanned aerial vehicle (UAV) equipped with a multispectral sensor to systematically acquire high-resolution growth imagery of winter wheat across critical phenological stages, from heading to maturity. The acquired multispectral imagery was meticulously annotated using the Labelme professional annotation tool to construct a comprehensive experimental dataset comprising over 2000 labeled images. These annotated data were subsequently employed to train an enhanced CNN model based on ResNet50 architecture, which achieved automated generation of panicle density maps and precise panicle counting, thereby realizing yield prediction. Field experimental results demonstrated significant yield variations among fertilization treatments under sufficient irrigation, with the 3:7 organic–inorganic blend achieving the highest actual yield (9363.38 ± 468.17 kg ha<sup>−1</sup>) significantly outperforming other treatments (<i>p</i> < 0.05), confirming the synergistic effects of optimized nitrogen and water management. The enhanced CNN model exhibited superior performance, with an average accuracy of 89.0–92.1%, representing a 3.0% improvement over YOLOv8. Notably, model accuracy showed significant correlation with yield levels (<i>p</i> < 0.05), suggesting more distinct panicle morphological features in high-yield plots that facilitated model identification. The CNN’s yield predictions demonstrated strong agreement with the measured values, maintaining mean relative errors below 10%. Particularly outstanding performance was observed for the organic fertilizer with full irrigation (5.5% error) and the 7:3 organic-inorganic blend with sufficient irrigation (8.0% error), indicating that the CNN network is more suitable for these management regimes. These findings provide a robust technical foundation for precision farming applications in winter wheat production. Future research will focus on integrating this technology into smart agricultural management systems to enable real-time, data-driven decision making at the farm scale.https://www.mdpi.com/2073-4395/15/7/1755water–nitrogen couplingCNNwheat spike detectionyield estimationinterpretable accuracy |
| spellingShingle | Donglin Wang Yuhan Cheng Longfei Shi Huiqing Yin Guangguang Yang Shaobo Liu Qinge Dong Jiankun Ge Prediction of Winter Wheat Yield and Interpretable Accuracy Under Different Water and Nitrogen Treatments Based on CNNResNet-50 Agronomy water–nitrogen coupling CNN wheat spike detection yield estimation interpretable accuracy |
| title | Prediction of Winter Wheat Yield and Interpretable Accuracy Under Different Water and Nitrogen Treatments Based on CNNResNet-50 |
| title_full | Prediction of Winter Wheat Yield and Interpretable Accuracy Under Different Water and Nitrogen Treatments Based on CNNResNet-50 |
| title_fullStr | Prediction of Winter Wheat Yield and Interpretable Accuracy Under Different Water and Nitrogen Treatments Based on CNNResNet-50 |
| title_full_unstemmed | Prediction of Winter Wheat Yield and Interpretable Accuracy Under Different Water and Nitrogen Treatments Based on CNNResNet-50 |
| title_short | Prediction of Winter Wheat Yield and Interpretable Accuracy Under Different Water and Nitrogen Treatments Based on CNNResNet-50 |
| title_sort | prediction of winter wheat yield and interpretable accuracy under different water and nitrogen treatments based on cnnresnet 50 |
| topic | water–nitrogen coupling CNN wheat spike detection yield estimation interpretable accuracy |
| url | https://www.mdpi.com/2073-4395/15/7/1755 |
| work_keys_str_mv | AT donglinwang predictionofwinterwheatyieldandinterpretableaccuracyunderdifferentwaterandnitrogentreatmentsbasedoncnnresnet50 AT yuhancheng predictionofwinterwheatyieldandinterpretableaccuracyunderdifferentwaterandnitrogentreatmentsbasedoncnnresnet50 AT longfeishi predictionofwinterwheatyieldandinterpretableaccuracyunderdifferentwaterandnitrogentreatmentsbasedoncnnresnet50 AT huiqingyin predictionofwinterwheatyieldandinterpretableaccuracyunderdifferentwaterandnitrogentreatmentsbasedoncnnresnet50 AT guangguangyang predictionofwinterwheatyieldandinterpretableaccuracyunderdifferentwaterandnitrogentreatmentsbasedoncnnresnet50 AT shaoboliu predictionofwinterwheatyieldandinterpretableaccuracyunderdifferentwaterandnitrogentreatmentsbasedoncnnresnet50 AT qingedong predictionofwinterwheatyieldandinterpretableaccuracyunderdifferentwaterandnitrogentreatmentsbasedoncnnresnet50 AT jiankunge predictionofwinterwheatyieldandinterpretableaccuracyunderdifferentwaterandnitrogentreatmentsbasedoncnnresnet50 |