Scholarlink

<p>Agriculture has always played a crucial role in ensuring food security and sustainable development. However the growing population and increasing demand for food, there is a need for technology-based and sustainable agriculture. The given paper proposes an ensemble machine learning (ML) framework for predicting the best suited crop based on the physical and chemical properties using grasshopper optimization algorithm (GOA). The study collected soil samples of different variants of crop (wheat, rice and maize) to ensure the models’ generalizability. After pre-processing of the collected data, optimal features are selected to remove bias using GOA. GOA algorithm is inspired by the foraging and swarming behavior of grasshoppers in nature for solving numerical optimization issues. Then the model is trained using combined ML classifiers namely random forest (RF) and extreme gradient boosting (XGB). The results indicate that the proposed model can accurately predict best suited crop based on the soil’s properties, thereby outperforming existing techniques. The framework can assist farmers in making informed decisions about crop management and help them optimize their crop yields.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An ensemble framework for crop prediction based on soil’s physical and chemical properties using grasshopper optimization algorithm (GOA)

  • 期刊论文

  • 发表日期：

    2025年3月19日

查看全文
  • Jyoti Nanwal,
  • Preeti Sethi

摘要

Agriculture has always played a crucial role in ensuring food security and sustainable development. However the growing population and increasing demand for food, there is a need for technology-based and sustainable agriculture. The given paper proposes an ensemble machine learning (ML) framework for predicting the best suited crop based on the physical and chemical properties using grasshopper optimization algorithm (GOA). The study collected soil samples of different variants of crop (wheat, rice and maize) to ensure the models’ generalizability. After pre-processing of the collected data, optimal features are selected to remove bias using GOA. GOA algorithm is inspired by the foraging and swarming behavior of grasshoppers in nature for solving numerical optimization issues. Then the model is trained using combined ML classifiers namely random forest (RF) and extreme gradient boosting (XGB). The results indicate that the proposed model can accurately predict best suited crop based on the soil’s properties, thereby outperforming existing techniques. The framework can assist farmers in making informed decisions about crop management and help them optimize their crop yields.