Evaluation and Optimization of Prediction Models for Crop Yield in Plant Factory

This study focuses on enhancing crop yield prediction in plant factory environments through precise crop canopy image capture and background interference removal. This method achieves highly accurate recognition of the crop canopy projection area (CCPA), with a coefficient of determination (R<sup...

Full description

Saved in:
Bibliographic Details
Main Authors: Yaoqi Peng, Yudong Zheng, Zengwei Zheng, Yong He
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Plants
Subjects:
Online Access:https://www.mdpi.com/2223-7747/14/14/2140
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849521433525354496
author Yaoqi Peng
Yudong Zheng
Zengwei Zheng
Yong He
author_facet Yaoqi Peng
Yudong Zheng
Zengwei Zheng
Yong He
author_sort Yaoqi Peng
collection DOAJ
description This study focuses on enhancing crop yield prediction in plant factory environments through precise crop canopy image capture and background interference removal. This method achieves highly accurate recognition of the crop canopy projection area (CCPA), with a coefficient of determination (R<sup>2</sup>) of 0.98. A spatial resolution of 0.078 mm/pixel was derived by referencing a scale ruler and processing pixel counts, eliminating outliers in the data. Image post-processing focused on extracting the canopy boundary and calculating the crop canopy area. By incorporating crop yield data, a comparative analysis of 28 prediction models was performed, assessing performance metrics such as MSE, RMSE, MAE, MAPE, R<sup>2</sup>, prediction speed, training time, and model size. Among them, the Wide Neural Network model emerged as the most optimal. It demonstrated remarkable predictive accuracy with an R<sup>2</sup> of 0.95, RMSE of 27.15 g, and MAPE of 11.74%. Furthermore, the model achieved a high prediction speed of 60,234.9 observations per second, and its compact size of 7039 bytes makes it suitable for efficient, real-time deployment in practical applications. This model offers substantial support for managing crop growth, providing a solid foundation for refining cultivation processes and enhancing crop yields.
format Article
id doaj-art-0a4cd51b1efd4d9e901f5228d6343d57
institution Kabale University
issn 2223-7747
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Plants
spelling doaj-art-0a4cd51b1efd4d9e901f5228d6343d572025-08-20T03:32:27ZengMDPI AGPlants2223-77472025-07-011414214010.3390/plants14142140Evaluation and Optimization of Prediction Models for Crop Yield in Plant FactoryYaoqi Peng0Yudong Zheng1Zengwei Zheng2Yong He3College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaKey Laboratory of Crop Drought Resistance Research of Hebei Province, Institute of Dryland Farming, Hebei Academy of Agriculture and Forestry Sciences, Hengshui 053000, ChinaSchool of Computer and Computing Science, Hangzhou City University, Hangzhou 310015, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaThis study focuses on enhancing crop yield prediction in plant factory environments through precise crop canopy image capture and background interference removal. This method achieves highly accurate recognition of the crop canopy projection area (CCPA), with a coefficient of determination (R<sup>2</sup>) of 0.98. A spatial resolution of 0.078 mm/pixel was derived by referencing a scale ruler and processing pixel counts, eliminating outliers in the data. Image post-processing focused on extracting the canopy boundary and calculating the crop canopy area. By incorporating crop yield data, a comparative analysis of 28 prediction models was performed, assessing performance metrics such as MSE, RMSE, MAE, MAPE, R<sup>2</sup>, prediction speed, training time, and model size. Among them, the Wide Neural Network model emerged as the most optimal. It demonstrated remarkable predictive accuracy with an R<sup>2</sup> of 0.95, RMSE of 27.15 g, and MAPE of 11.74%. Furthermore, the model achieved a high prediction speed of 60,234.9 observations per second, and its compact size of 7039 bytes makes it suitable for efficient, real-time deployment in practical applications. This model offers substantial support for managing crop growth, providing a solid foundation for refining cultivation processes and enhancing crop yields.https://www.mdpi.com/2223-7747/14/14/2140crop canopy imageplant factorycrop yield predictionWide Neural Network
spellingShingle Yaoqi Peng
Yudong Zheng
Zengwei Zheng
Yong He
Evaluation and Optimization of Prediction Models for Crop Yield in Plant Factory
Plants
crop canopy image
plant factory
crop yield prediction
Wide Neural Network
title Evaluation and Optimization of Prediction Models for Crop Yield in Plant Factory
title_full Evaluation and Optimization of Prediction Models for Crop Yield in Plant Factory
title_fullStr Evaluation and Optimization of Prediction Models for Crop Yield in Plant Factory
title_full_unstemmed Evaluation and Optimization of Prediction Models for Crop Yield in Plant Factory
title_short Evaluation and Optimization of Prediction Models for Crop Yield in Plant Factory
title_sort evaluation and optimization of prediction models for crop yield in plant factory
topic crop canopy image
plant factory
crop yield prediction
Wide Neural Network
url https://www.mdpi.com/2223-7747/14/14/2140
work_keys_str_mv AT yaoqipeng evaluationandoptimizationofpredictionmodelsforcropyieldinplantfactory
AT yudongzheng evaluationandoptimizationofpredictionmodelsforcropyieldinplantfactory
AT zengweizheng evaluationandoptimizationofpredictionmodelsforcropyieldinplantfactory
AT yonghe evaluationandoptimizationofpredictionmodelsforcropyieldinplantfactory