LANZHOU -- Chinese scientists have developed a high-precision gridded precipitation dataset to support climate and precipitation research in alpine cold regions, according to the Northwest Institute of Eco-environment and Resources (NIEER) under the Chinese Academy of Sciences.

Using artificial intelligence, the researchers at NIEER created a new framework called Three-Layer Intelligent Downscaling and Calibration (TLIDC) to produce detailed precipitation data specifically tailored for these extreme environments, said Qin Xiang, a researcher at the institute.

The researchers have completed the quantitative evaluation of this new framework by using data from 100 rain gauge stations in the Qilian Mountains, a key ecological shield in western China, which straddles the border between northwestern Gansu and Qinghai provinces.

The framework was used to reconstruct daily precipitation data for the mountain range spanning the period from 1950 to 2024.

The new framework can produce reliable, high-precision precipitation data with accuracy surpassing that of current mainstream datasets. It helps reduce errors in regional precipitation estimates caused by the limited availability of ground-based observations, according to the study.

Accurate precipitation data are vital to hydrological and climate studies, especially for alpine cold regions where in-situ observational data are limited, according to Qin.

"This type of new dataset provides a viable solution for generating high-precision precipitation data in alpine cold regions with complex topography and sparse observational networks, addressing a critical gap in current climate and hydrological research," Qin said.

The findings of the study have been published in the journal Atmospheric Research.