Sowing Intelligence: Advancements in Crop Yield Prediction Through Machine Learning and Deep Learning Approaches DOI
Sivaraman Jayanthi,

D. Tamil Priya,

Naresh Goud M

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 27, 2024

Abstract Ensuring global food security necessitates precise crop yield prediction for informed agricultural planning and resource allocation. We investigated the impact of temperature, rainfall, pesticide application on using a comprehensive, multi-year, multi-region dataset. Our research rigorously compared, first time, effectiveness fifteen different algorithms encompassing both established machine learning deep architectures, particularly Recurrent Neural Network (RNN), in constructing robust CYP models. Through rigorous experimentation hyperparameter tuning, we aimed to identify most optimal model accurate prediction. leveraged comprehensive dataset various attributes, including geographical coordinates, varieties, climatic parameters, farming practices. To ensure effectiveness, preprocessed data, handling categorical variables, standardizing numerical features, dividing data into distinct training testing sets. The experimental evaluation revealed that Random Forest achieved highest accuracy, with an impressive (R²=0.99). However, XGBoost offered compelling trade-off slightly lower accuracy (R²=0.98) but significantly faster inference times (0.36s 0.02s, respectively), making it suitable real-world scenarios limited computational resources. While emerged as efficient solution this investigation, also explored potential approaches, RNNs, prediction, paving way future even greater accuracy.

Language: Английский

Research and Analysis of the Application of Machine Learning in Agricultural Development DOI Creative Commons

Yimin Yuan

Transactions on Computer Science and Intelligent Systems Research, Journal Year: 2024, Volume and Issue: 5, P. 1035 - 1042

Published: Aug. 12, 2024

Agriculture is the most basic, fundamental and important industry. Now, amid global climate change resource shortages, agriculture must deal with challenges of growing demand as world's population increases This article organizes three aspects that need improvement: anticipatory preparation before production, improvement production methods, detection classification agricultural products, analyzes how machine learning can help progress in these aspects. Residual deep convolution spatial pyramid pooling algorithms be used to detect plant pests diseases. The RF algorithm, XGBoost LightGBM algorithm CatBoos generate landslide susceptibility maps. Deep learning, convolutional neural networks, support vector machines identify hybrid wheat. Through this research, it determined great development, development mutual. significance study lies face problems.

Language: Английский

Citations

0
Sowing Intelligence: Advancements in Crop Yield Prediction Through Machine Learning and Deep Learning Approaches DOI
Sivaraman Jayanthi,

D. Tamil Priya,

Naresh Goud M

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 27, 2024

Abstract Ensuring global food security necessitates precise crop yield prediction for informed agricultural planning and resource allocation. We investigated the impact of temperature, rainfall, pesticide application on using a comprehensive, multi-year, multi-region dataset. Our research rigorously compared, first time, effectiveness fifteen different algorithms encompassing both established machine learning deep architectures, particularly Recurrent Neural Network (RNN), in constructing robust CYP models. Through rigorous experimentation hyperparameter tuning, we aimed to identify most optimal model accurate prediction. leveraged comprehensive dataset various attributes, including geographical coordinates, varieties, climatic parameters, farming practices. To ensure effectiveness, preprocessed data, handling categorical variables, standardizing numerical features, dividing data into distinct training testing sets. The experimental evaluation revealed that Random Forest achieved highest accuracy, with an impressive (R²=0.99). However, XGBoost offered compelling trade-off slightly lower accuracy (R²=0.98) but significantly faster inference times (0.36s 0.02s, respectively), making it suitable real-world scenarios limited computational resources. While emerged as efficient solution this investigation, also explored potential approaches, RNNs, prediction, paving way future even greater accuracy.

Language: Английский

Citations

0