Machine Learning-Based Yield and Harvest Timing Prediction for High-Value Horticultural Crops Under Variable Environmental Conditions
Year: 2026
Type: article
Abstract: Accurate prediction of crop yield and harvest timing is essential for improving production planning, resource allocation, and postharvest management in high-value horticultural crops. However, yield and maturity are strongly influenced by variable environmental conditions, including temperature, rainfall, humidity, soil characteristics, and crop growth dynamics, making conventional prediction approaches less responsive to changing field conditions. This study aims to develop a machine learning-based predictive framework for estimating crop yield and harvest timing by integrating crop growth and environmental variables. The proposed approach utilizes historical horticultural production data combined with meteorological and environmental observations as input features. Several machine learning algorithms are evaluated and compared based on their predictive performance using appropriate regression and classification or temporal prediction metrics. The framework is designed to identify the environmental and crop-related variables that contribute most strongly to yield and harvest timing predictions while capturing nonlinear relationships within the data. The expected results provide an integrated prediction approach that can support more accurate yield estimation and timely harvest decisions under variable environmental conditions. The proposed framework is expected to contribute to precision horticulture by providing data-driven information for crop management, harvest planning, and efficient utilization of agricultural resources.
Source: Agricultural Power Journal
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDG: Zero hunger
Open Access status: hybrid
OpenAlex ID: W7236859210
