Predicting soil moisture content of tea plantation using support vector machine optimized by arithmetic optimization algorithm

Abstract

Soil moisture content (SMC) is an important parameter that affects tea growth. Reasonable soil moisture content improves tea quality and ensures tea yield. Therefore, it is necessary to regularly monitor the soil water content. However, the traditional soil moisture content prediction algorithm has the problems of low accuracy and low efficiency. This paper constructs and evaluates the performance of a hybrid arithmetic optimization algorithm (AOA) and support vector machine (SVM) prediction model (AOA-SVM) for predicting SMC in tea plantations. Grey relation analysis (GRA) and Pearson correlation analysis are adopted to select features for soil moisture content prediction model, and then the correlation of SMC with soil temperature (ST), atmospheric temperature (AT), and soil electrical conductivity (SEC) was analyzed. The optimal penalty parameter ( c) and the parameter of the kernel function ( g) of SVM model are determined by AOA. The mean square error (MSE) and coefficient of determination ([Formula: see text]), mean absolute error (MAE), and mean error (ME) were calculated to evaluate the performance of the model. Meanwhile, the performance of AOA-SVM model is compared with SVM optimized by the sparrow search algorithm (SSA-SVM), extreme learning machine (ELM), support vector machine (SVM), and convolutional neural networks (CNN). The results showed that AOA-SVM, SSA-SVM and CNN are better, with the coefficient of determination above 93%, the coefficient of determination of SVM and ELM is 81.69% and 89.61%, respectively. The AOA-SVM model has the best R2 of 95.03%. This indicates that the AOA-SVM model has significant performance with higher R2, smaller MSE than other models, which has potential implications in precision agriculture.

TEA SOIL: Self-Power IoT for Precision Soil Farming of Tea Plant Cultivation

“…In 2023 Yin, D., et al, [16] presented a technique based on integration of SVM and AOA detection to detect soil moisture in tea estates. Pearson correlation analysis and grey relation analysis (GRA) are used to predict the moisture of soil.…”

Classification of EEG Signals Based on Sparrow Search Algorithm-Deep Belief Network for Brain-Computer Interface

“…The procedural steps of the algorithm are illustrated in Figure 3. The computational trajectory of the algorithm unfolds as follows [27]: First, represent a population of 𝑛 Sparrows as 𝑛 × 𝑑 -d-dimensional vectors using matrices,…”

“…where 𝑓 and 𝑓 represent the global best fitness value and the global worst fitness value, respectively. The computational trajectory of the algorithm unfolds as follows [27]: First, represent a population of n Sparrows as n × d -d-dimensional vectors using matrices,…”

“…This process repairs connections between damaged neurons via neural plasticity, leading to classifiers, comparing the results with those from three traditional classifiers, namely CNN and SVM. The SSA-SVM classifier exhibited significant improvements overall [27]. The SSA algorithm, with its dual strengths in global and local search capabilities, effectively determines the hyperparameters of DBN, thus addressing DBN networks' limitations.…”

Prediction of soil moisture using BiGRU-LSTM model with STL decomposition in Qinghai–Tibet Plateau

“…For instance, Togneri et al (2022) introduced a model based on LightGBM and sensor network data, while Luo, Wen & He (2023) proposed a model based on back propagation (BP) neural networks and optical and thermal infrared (TIR) spectroscopy. Zhu et al (2023) presented a model based on random forests (RF) and climate observation data such as evapotranspiration, and Yin, Wang & Huang (2023) proposed a method based on support vector machines (SVM) and soil state data such as soil temperature. Moreover, several researchers have explored the integration of various observation data from different sources, including satellite data, sensor data, and in situ data, to establish numerous soil moisture prediction models for diverse application scenarios.…”