Machine Learning for Detecting Fertilizer Solution Information Based on Dielectric Frequency Response

Rapid detection of fertilizer solutions is essential for improving water-fertilizer integration systems. However, existing detection methods are hindered by high costs, complexity, and slow response times, making real-time monitoring challenging. To solve these issues, we developed a qualitative-quantitative model that leverages machine learning (ML) algorithms based on the dielectric frequency response to detect the type and concentration of seven fertilizer solutions (N, P, K, PN, PK, NK, and NPK). Each fertilizer had unique dielectric frequency features, with different fluctuation, peak numbers, and maximum peaks. A linear relationship was also observed between the dielectric features (gain or phase shift) and fertilizer concentration within a specific frequency band. Following a “qualitative first, then quantitative” strategy, a qualitative-quantitative model was constructed using these results, including one classification model and seven concentration prediction models. For identifying solution types, the random forest (RF) algorithm was selected as the optimal qualitative model, with an accuracy of 98.57%. For detecting solution concentrations, seven optimal models were identified with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$R^{{2}}$ </tex-math></inline-formula> values exceeding 0.98 and root-mean-square error (RMSE) values below 0.4%, each incorporating the observed linear relationships mentioned above and different ML algorithms. Notably, the least-squares support vector machine (LSSVM) and backpropagation (BP) regression models outperformed the partial least-squares regression (PLSR) model. These results demonstrated that the developed qualitative-quantitative model effectively integrates dielectric features with ML algorithms to accurately detect fertilizer solution components. This model can provide feedback on fertilizer information, supporting rapid online identification of fertilizer components and significantly enhancing their water-fertilizer utilization efficiency.