Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Chuanfeng Liu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Reinterpreting terrestrial ‘warming holes’ in the context of the near-surface atmospheric energy balance

    by Paul C Stoy, Chuanfeng Liu, Kiran V Menon, Gwendolyn Murphy, Mikki S Wilburn, Connie Zhao

    Some terrestrial regions have cooled despite increases in global average near-surface air temperature. It is important to study these ‘warming holes’ to understand regional climate processes and to develop strategies to mitigate global change impacts. Many warming holes have occurred in places with changes to regional hydrology. As a consequence, increases to latent heating due to shifts in specific humidity may obscure changes due to temperature (enthalpy) when studying the full energy budget of the near surface atmosphere. We ask if known warming holes in the southeastern U.S. (SEUS), northern North American Great Plains (NNAGP), and southeastern China result from such ‘water-for-temperature’ tradeoffs using a Bayesian approach that accounts for both temporal and spatial autocorrelation in climatic variables from ERA5. The SEUS warming hole lost more energy (up to −100 J kg −1 yr −1 ) than apparent from temperature trends alone, as it also became drier. The NNAGP exhibited the well known transition along the 100th meridian in which the semi-arid west lost enthalpy and latent heat, and the humid east gained near-surface atmospheric energy; these patterns were not apparent from temperature trends alone. Increases in latent heat of 50 J kg −1 yr −1 or more in the southern part of the southeastern China study area shifted significant trends in near-surface atmospheric energy further north than what was revealed by temperature trends alone. The magnitude of trends in latent heat often exceeded those of enthalpy across all study areas, emphasizing the importance of incorporating water and a more complete depiction of the energy balance into studies of regional climate.

  • Open Access

    Integrating Machine Learning and a Spatial Contextual Algorithm to Detect Wildfire from Himawari-8 Data in Southwest China

    by Chuanfeng Liu, Rui Chen, Binbin He

    Timely wildfire detection is helpful for fire monitoring and fighting. However, the available wildfire products with high temporal resolutions face problems, such as high omission error and commission error (false alarm) rates. This study proposed a wildfire detection algorithm combined with an improved spatial contextual algorithm and machine learning method in southwest China. First, a dataset consisting of a formation of high-confidence fire pixels combining the WLF (Himawari Wild Fire product) and VIIRS wildfire products was constructed. Then, a model to extract potential fire pixels was built using the random forest method. Additionally, an improved spatial contextual algorithm was used to identify actual fire pixels from potential fire pixels. Finally, strategies such as sun glint rejection were used to remove false alarms. As a result, the proposed algorithm performed better, with both a lower omission error rate and a lower commission error rate than the WLF product. It had a higher F1 score (0.47) than WLF (0.43) with VIIRS for reference, which means it is more suitable for wildfire detection.