Latest

Humidity

Research Finds Hybrid Model for Adaptive Temperature and Humidity Forecasting in Solar Greenhouses

Researchers from Shenyang Agricultural University have developed a new RIME-optimized CNN-BiLSTM hybrid model for precise climate forecasting to protect agriculture. This model addresses the challenges of large diurnal temperature difference and extreme weather in Northeast China, which can significantly impact crop production. By using Pearson correlation analysis and the RIME

Inland water pollution

Innovative Approach to Identifying Urban River Pollution Sources Using Deep Learning and Data Assimilation

Researchers from Hohai University have developed a novel method to identify pollution sources in urban rivers, leveraging the combination of deep learning (DL) and data assimilation (DA) techniques. This approach addressed the challenges of traditional methods, which often require high computational demands and struggle with equifinality. The study evaluated three

Building materials industry

Data-Driven Approach Optimizes Compressive Strength of Solid-Waste-Based Calcium Sulfoaluminate Cement

A team of researchers at Shandong University has employed a machine-learning (ML) approach to analyze the factors affecting the strength of solid-waste-based calcium sulfoaluminate cement (CSA). This data-driven analysis has led to significant improvements in the compressive strength of CSA, making it a promising low-carbon building material. The study found