Hybrid Whale Archimedes Optimization-based MLPNN model for soil nutrient classification and pH prediction

Area of Science:

• Agricultural Science
• Environmental Science
• Computer Science

Background:

• Soil fertility and environmental factors are crucial for agricultural productivity and crop quality.
• Accurate prediction and classification of soil nutrients and pH levels are essential for sustainable agriculture.

Purpose of the Study:

• To propose a novel Hybrid Whale Archimedes Optimization-based Multilayer Perceptron Neural Network (HWAO-MLPNN) model for soil nutrient and pH classification.
• To enhance soil health, minimize harmful fertilizer application, improve environmental quality, and increase agricultural profits.

Main Methods:

• The HWAO-MLPNN model integrates the Multilayer Perceptron Neural Network (MLPNN) with the Hybrid Whale Archimedes Optimization (HWAO) algorithm.
• Soil samples from villages were analyzed for key nutrients like phosphorous (P), organic carbon (OC), boron (B), and potassium (K).
• The Marathwada dataset was used for validation, employing metrics such as accuracy, cross-validation accuracy, AUC, MSE, G-mean, precision, specificity, and sensitivity.

Main Results:

• The HWAO-MLPNN model achieved high classification accuracy for pH levels (98.1%) and soil nutrients (97.9%).
• Cross-validation accuracy reached 98.3% for pH classification and 97.9% for soil nutrient classification.
• The model demonstrated superior performance compared to existing methods in classifying soil properties.

Conclusions:

• The HWAO-MLPNN model provides an effective tool for accurate soil nutrient and pH level classification.
• Implementing this model can lead to significant improvements in soil health and environmental quality.
• The accurate classification supports reduced fertilizer usage and enhanced profitability in the agricultural sector.