Scholarlink

Soil is essential to the environmental process and growing crops. An accurate assessment of soil chemical characteristics is essential for agricultural and land management decisions to be well-informed. Precision agriculture has advanced significantly because of machine learning. It uses automation and data-driven insights to improve several facets of agricultural methods, fostering effectiveness, sustainability, and productivity. The “Land Use/Cover Area Frame Statistical Survey Soil” (LUCAS) is a comprehensive and frequent topsoil survey conducted throughout the European Union to get data pertinent to policy about how land management affects soil properties. The data covers 28 European Union States. This paper analyzes and predicts the chemical properties of the soil of Hungary based on the LUCAS 2015 dataset that includes calcium carbonates (CaCO3), nitrogen (N), phosphorus (P), potassium (K), electrical conductivity (EC), pH. It estimates them using LUCAS and Landsat 8 satellite images by using different regression-based algorithms like partial least square regression (PLSR), Gaussian process regression (GPR), support vector regression (SVR), multilayer perceptron (MLP), AdaBoost, ridge and compares them. The Lucas survey data points and Landsat 8 satellite images (multispectral) are integrated for forecasting different soil nutrients, expanding the model’s relevance to diverse agricultural and environmental applications. The algorithms undergo evaluation, producing acceptable Root Mean Squared Error (RMSE) and Ratio of Performance to Prediction (RPD) values. The proposed approach can estimate the chemical properties of the soil samples in Hungary replacing the orthodox method of laboratory analysis with the soil samples’ spectral image.

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

A Machine Learning-Based Approach for Soil Chemical Property Estimation Using Multispectral Data in Hungary

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Sourav Seal,
  • Divyashikha Sethia

摘要

Soil is essential to the environmental process and growing crops. An accurate assessment of soil chemical characteristics is essential for agricultural and land management decisions to be well-informed. Precision agriculture has advanced significantly because of machine learning. It uses automation and data-driven insights to improve several facets of agricultural methods, fostering effectiveness, sustainability, and productivity. The “Land Use/Cover Area Frame Statistical Survey Soil” (LUCAS) is a comprehensive and frequent topsoil survey conducted throughout the European Union to get data pertinent to policy about how land management affects soil properties. The data covers 28 European Union States. This paper analyzes and predicts the chemical properties of the soil of Hungary based on the LUCAS 2015 dataset that includes calcium carbonates (CaCO3), nitrogen (N), phosphorus (P), potassium (K), electrical conductivity (EC), pH. It estimates them using LUCAS and Landsat 8 satellite images by using different regression-based algorithms like partial least square regression (PLSR), Gaussian process regression (GPR), support vector regression (SVR), multilayer perceptron (MLP), AdaBoost, ridge and compares them. The Lucas survey data points and Landsat 8 satellite images (multispectral) are integrated for forecasting different soil nutrients, expanding the model’s relevance to diverse agricultural and environmental applications. The algorithms undergo evaluation, producing acceptable Root Mean Squared Error (RMSE) and Ratio of Performance to Prediction (RPD) values. The proposed approach can estimate the chemical properties of the soil samples in Hungary replacing the orthodox method of laboratory analysis with the soil samples’ spectral image.