A dual-source data-driven gated spatiotemporal fusion network significantly enhances the accuracy of fine-scale lightning forecasting based on weather foundation models
Peer-Reviewed Publication
Updates every hour. Last Updated: 5-Nov-2025 13:11 ET (5-Nov-2025 18:11 GMT/UTC)
In a paper published in SCIENCE CHINA Earth Sciences, a team of researchers investigated a fine-scale lightning forecasting approach based on weather foundation models (WFMs) and proposed a dual-source data-driven forecasting framework that integrates the strengths of both WFMs and recent lightning observations to enhance predictive performance. Furthermore, a gated spatiotemporal fusion network (gSTFNet) is designed to address the challenges of cross-temporal and cross-modal fusion inherent in dual-source data integration. Experimental results demonstrate that the dual-source framework significantly improves forecasting performance compared to models trained solely on WFMs and outperforms both the ECMWF HRES lightning product and other deep-learning spatiotemporal forecasting models.
An accurate map of intracellular organelle pH is crucial for comprehending cellular metabolism and organellar functions. However, a unified intracellular pH spectrum using a single probe is still lacking. Now, writing in the journal Science China Life Sciences, a team of researchers from Jian-Sheng Kang developed a novel quantum entanglement-enhanced pH-sensitive probe called SITE-pHorin (single excitation and two emissions pH sensor protein), which features a wide pH-sensitive range and ratiometric quantitative measurement capabilities. They subsequently measured the pH of various organelles and their subcompartments, including mitochondrial subspaces, Golgi stacks, endoplasmic reticulum (ER), lysosomes, peroxisomes, and endosomes in COS-7 cells.
A research team has developed an advanced computer vision model that can detect the precise growth points of weeds in cornfields with unprecedented accuracy.
A research team has developed advanced methodologies for predicting the aboveground biomass (AGB) of corn by integrating unmanned aerial vehicles (UAVs), multi-sensor data, and machine learning models.
A research team has now introduced the concept of the photochemical compensation point (PCCP), a novel measure that identifies the light level at which energy used for photosynthesis equals that dissipated non-photochemically.
A research team sheds light on how canopy structure and photosynthetic traits in coniferous forests respond to thinning, drought, and rising temperatures.
A new study introduces a universal two-stage method that successfully segments plant stems and leaves across both monocotyledonous and dicotyledonous crops.
A research team has demonstrated that greenhouse tomato productivity can be significantly improved by targeting leaf-level efficiency and plant layout strategies.
Recently, the team pf researchers led by Professor Wen Xu from China Agricultural University took the Haixi area of the Erhai Lake Basin as the research object. By integrating farmer surveys, literature materials and statistical data, they systematically quantified the emissions of four pollutants, namely ammonia nitrogen (NH3-N), total nitrogen (TN), total phosphorus (TP) and chemical oxygen demand (COD), from agricultural production and rural domestic sewage in this area in 2022. The related paper has benn published in Frontiers of Agricultural Science and Engineering (DOI: 10.15302/J-FASE-2025622).