Welcome to Zhen Zhang’s Research Group
I am a researcher at the National Tibetan Plateau Data Center (TPDC), Institute of Tibetan Plateau Research, Chinese Academy of Sciences. My work focuses on global change big data, Earth system modeling, remote sensing, and methane cycling, with an emphasis on model development and interdisciplinary data integration. I develop numerical models and leverage remote sensing, machine learning, and multi-model approaches to analyze complex climate feedback mechanisms, particularly in relation to methane science questions.
Get Andrew’s letters delivered to your inbox every week.
ProjectsView all
- Wetland inundation dynamics
Machine learning is a very successful technology but applying it today often requires spending substantial effort hand-designing features. This is true for applications in vision, audio and text. To address this, Ng’s group and others are working on “deep learning” algorithms, which can automatically learn feature representations (often from unlabeled data) thus avoiding a lot of time-consuming engineering. These algorithms are based on building massive
- Dynamics of global Wetland CH4 emissions
This is an example showing the simulated monthly wetland CH4 fluxes and the freeze/thaw cycle. The wetland CH4 fluxes is estimated using a prognostic semi-empirical approach incorporated into LPJ-wsl model. Check out our paper on Biogeosciences for more details.
- Feedback of wetland CH4 in projected future
Wetland CH4 feedback was assumed to be muted in the future climate scenarios in previous climate projection. We use climate and vegetation models to provide a comprehensive assessment and find that climate change could cause shifting dominances of global climate forcing from anthropogenic to wetland CH4 emissions during the 21st century. Check out our recent publication on Proceedings of the National Academy of Sciences for more details.
PublicationsView all
Machine Learning Specialization
Scaling up deep learning algorithms has been shown to lead to increased performance in benchmark tasks and to enable discovery of complex high-level features. Recent efforts to train extremely large networks
CoursesView all
Courses View all
Deep Learning Breakthroughs
Discover the latest advancements in deep learning research.