article · Neural Computing and Applications
Crop yield prediction is essential for agricultural planning across local, regional, and international scales. The Crop Yield Prediction Algorithm combines Internet of Things techniques with big data to analyse field conditions, climate, weather, and chemical variables. Five machine learning models were trained and verified using optimal hyper-parameter settings. Among the tested approaches, the ExtraTreeRegressor achieved the highest performance score of 0.9933, while the RandomForestRegressor scored 0.9903 and the DecisionTreeRegressor scored 0.9814. In addition, an active learning algorithm was incorporated into the system to decrease the volume of labelled data required for model training. This enhancement improves both the efficiency and accuracy of yield estimations, supporting better decision-making for agricultural stakeholders facing seasonal challenges such as nutrient deficits, pests, and climate shifts.
Predicting harvest outcomes accurately helps farmers and policymakers prepare for food supply fluctuations caused by environmental stress and changing weather patterns. By using smart data collection alongside machine learning that requires fewer manually labelled records, these predictive methods offer practical pathways to make precision agriculture tools more accessible, efficient, and dependable for agricultural planners at every level.
The algorithm is designed for predictive agricultural software aimed at farmers and government policymakers assessing annual crop outputs. The technology sits at an applied and tested research stage, having validated multiple machine learning models and an active learning framework on agricultural datasets. Commercial adoption would require integration into existing agricultural management systems, connected sensor hardware, and digital advisory platforms.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Agriculture faces a significant challenge in predicting crop yields, a critical aspect of decision-making at international, regional, and local levels. Crop yield prediction utilizes soil, climatic, environmental, and crop traits extracted via decision support algorithms. This paper presents a novel approach, the Crop Yield Prediction Algorithm (CYPA), utilizing IoT techniques in precision agriculture. Crop yield simulations simplify the comprehension of cumulative impacts of field variables such as water and nutrient deficits, pests, and illnesses during the growing season. Big data databases accommodate multiple characteristics indefinitely in time and space and can aid in the analysis of meteorology, technology, soils, and plant species characterization. The proposed CYPA incorporates climate, weather, agricultural yield, and chemical data to facilitate the anticipation of annual crop yields by policymakers and farmers in their country. The study trains and verifies five models using optimal hyper-parameter settings for each machine learning technique. The DecisionTreeRegressor achieved a score of 0.9814, RandomForestRegressor scored 0.9903, and ExtraTreeRegressor scored 0.9933. Additionally, we introduce a new algorithm based on active learning, which can enhance CYPA's performance by reducing the number of labeled data needed for training. Incorporating active learning into CYPA can improve the efficiency and accuracy of crop yield prediction, thereby enhancing decision-making at international, regional, and local levels.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s00521-023-08619-5
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
