Climate impact assessment, agricultural planning, and disaster preparedness requires accurate long-term prediction of temperature and rainfall. Conventional statistical models are frequently not able to represent nonlinear and long-term relationships in climate data, and deep learning models, however powerful in prediction, cannot be interpreted. The given paper suggests an interpretable deep learning architecture, which uses Long Short-Term Memory (LSTM) networks and SHAP-based explainability to forecast multivariate climate. Sliding window sequences are used to process historical data (temperature, rainfall, humidity and atmospheric pressure) to obtain seasonal and long-term trends. The proposed model predicts both temperature and rainfall simultaneously, and it has a better performance than the ARIMA, LSTM, GRU and CNN-LSTM models in the terms of RMSE, MAE and Accuracy. Moreover, the explainability module offers insights into feature and time importance, which increases the level of transparency and trust in the prediction. Empirical evidence shows that the described method is effective in balancing predictive accuracy of 92% and understandability, which can be used in climate decision support systems.
Harsh Pratap Singh, S. Meena, Jahar Singh Lodhi et al.· 2026 International Conferenc...· 0 citations
Demand for solar-based microgrid systems is increasing in remote and rural areas due to their simple installation and operation flexibility. Power quality issues arise in the solar supply system because of the switching of inverters, nonlinear loads, and fluctuation in solar irradiance. This study proposes an integrated artificial intelligence and Internet of Things-based smart power quality management system for a solar microgrid. A MATLAB simulation model of a 20 kW solar microgrid is developed, incorporating a DC–DC boost converter and a maximum power point tracking system for improving the power conversion efficiency. An IoT monitoring system continuously monitors real-time data of supply voltage, current, power factor, and total harmonic distortion. These measures are processed using an artificial neural network- long short-term memory-based intelligent controller to detect power quality disturbances by analyzing the sensor data and making quick control decisions. The proposed MATLAB Simulink microgrid model is validated through hardware-in-the-loop testing on the Typhoon hardware-in-the-loop platform. The experimental results of hardware-in-the-loop demonstrate a 70% total harmonic distortion reduction (to 3%), power factor (0.99), and settling time less than 50 ms that is under irradiance/load dynamics, outperforming baselines and meeting IEEE 519/1547 standards. Hardware-in-the-loop results show less than 5% deviation, demonstrating suitability for deployment.
Nagendra Singh, Andrei Dzeikalo, Bhagyanagar Rajagopal et al.· International journal of mat...· 0 citations