diff --git a/content/news/2604Gregory.md b/content/news/2604Gregory.md index b74508da..fbbf4aee 100644 --- a/content/news/2604Gregory.md +++ b/content/news/2604Gregory.md @@ -9,4 +9,4 @@ images: ['images/news/2604FloeNet.gif'] link: 'https://doi.org/10.1029/2026GL122981' --- -The sea ice emulator we featured a few months back, **FloeNet**, is now officially published in GRL. Led by **Will Gregory**, the graph neural network emulates GFDL's global sea ice model (SIS2) while conserving mass, reproducing sea ice and snow-on-ice trends and variability with volume anomaly correlations above 0.96 in the Antarctic and 0.76 in the Arctic across a range of forcing scenarios. [Read the paper](https://doi.org/10.1029/2026GL122981). \ No newline at end of file +The sea ice emulator we featured a few months back, **FloeNet**, is now officially published in GRL. Led by **Will Gregory**, the graph neural network emulates GFDL's global sea ice model (SIS2) while conserving mass, reproducing sea ice and snow-on-ice trends and variability with volume anomaly correlations above 0.96 in the Antarctic and 0.76 in the Arctic across a range of forcing scenarios. [Read the paper](https://doi.org/10.1029/2026GL122981). diff --git a/content/news/2608Chapman.md b/content/news/2608Chapman.md index 6e682a75..123ac516 100644 --- a/content/news/2608Chapman.md +++ b/content/news/2608Chapman.md @@ -9,4 +9,4 @@ images: ['images/news/2608-Chapman.png'] link: 'https://doi.org/10.48550/arXiv.2607.18416' --- -**Will Chapman** et al. investigate an important challenge in developing **physically consistent AI weather and climate emulators.** The [study](https://doi.org/10.48550/arXiv.2607.18416) shows that enforcing exact water-budget conservation during training can inadvertently allow precipitation biases to grow, even when the final corrected output appears physically perfect. By introducing a revised training strategy that supervises the raw model predictions while penalizing budget imbalances, the authors **restore stable learning** and demonstrate that **exact budget closure alone is not sufficient to ensure physically meaningful AI models.** \ No newline at end of file +**Will Chapman** et al. investigate an important challenge in developing **physically consistent AI weather and climate emulators.** The [study](https://doi.org/10.48550/arXiv.2607.18416) shows that enforcing exact water-budget conservation during training can inadvertently allow precipitation biases to grow, even when the final corrected output appears physically perfect. By introducing a revised training strategy that supervises the raw model predictions while penalizing budget imbalances, the authors **restore stable learning** and demonstrate that **exact budget closure alone is not sufficient to ensure physically meaningful AI models.** diff --git a/content/news/2608Shamekh.md b/content/news/2608Shamekh.md index 9e5c3bef..52a00c96 100644 --- a/content/news/2608Shamekh.md +++ b/content/news/2608Shamekh.md @@ -11,4 +11,4 @@ link: 'https://doi.org/10.1175/JAS-D-25-0178.1' **Sara Shamekh** and collaborators present a **[new machine learning framework](https://doi.org/10.1175/JAS-D-25-0178.1)** that combines probabilistic modeling with symbolic equation discovery to uncover how **different types of tropical rainfall—shallow convective, deep convective, and stratiform—depend on large-scale atmospheric conditions**. Using satellite observations and reanalysis data, the study derives compact, physically interpretable equations that capture key environmental controls on rain area, providing **new insights into tropical convection** and paving the way for **more realistic, stochastic precipitation parameterizations in climate models.** -Read the paper [here](/files/Shamekh_et_al.2026.pdf) \ No newline at end of file +Read the paper [here](/files/Shamekh_et_al.2026.pdf) diff --git a/content/news/2608Zanna.md b/content/news/2608Zanna.md index 98477d25..3b9c0772 100644 --- a/content/news/2608Zanna.md +++ b/content/news/2608Zanna.md @@ -10,4 +10,3 @@ link: 'https://www.simonsfoundation.org/2026/08/05/at-the-simons-science-summit- --- At the 2026 Simons Science Summit, our own **Laure Zanna** joined a panel on how AI is helping tackle complex systems in climate, fusion, and aerospace. Zanna described using AI to connect small-scale ocean processes with large-scale dynamics, helping researchers capture the vast range of scales needed to understand how the ocean works. Read the full recap: **[At the Simons Science Summit, Leaders Explore How AI Is Transforming Scientific Discovery.](https://www.simonsfoundation.org/2026/08/05/at-the-simons-science-summit-leaders-explore-how-ai-is-transforming-scientific-discovery/)** - diff --git a/content/team/JinchangLi.md b/content/team/JinchangLi.md new file mode 100644 index 00000000..bbac43f4 --- /dev/null +++ b/content/team/JinchangLi.md @@ -0,0 +1,14 @@ +--- +title: "Jinchang 'Thomas' Li" +draft: false +image: "/images/team/JinchangLi.png" +jobtitle: "Affiliate, undergraduate Student" +promoted: true +weight: 28 +Website: 'https://github.com/ThomasLi0314' +Position: +tags: [Ocean, Atmosphere, Machine Learning] +--- + + +NYU diff --git a/content/team/YuanpuLi.md b/content/team/YuanpuLi.md new file mode 100644 index 00000000..fee16e08 --- /dev/null +++ b/content/team/YuanpuLi.md @@ -0,0 +1,14 @@ +--- +title: "Yuanpu Li" +draft: false +image: "/images/team/YuanpuLi.jpeg" +jobtitle: "Postdoc" +promoted: true +weight: 20 +Website: +position: +tags: [Atmosphere, Machine Learning, Climate Model Development] +--- + + +CU Boulder diff --git a/static/images/team/JinchangLi.png b/static/images/team/JinchangLi.png new file mode 100644 index 00000000..769262d3 Binary files /dev/null and b/static/images/team/JinchangLi.png differ diff --git a/static/images/team/YuanpuLi.jpeg b/static/images/team/YuanpuLi.jpeg new file mode 100644 index 00000000..59742c70 Binary files /dev/null and b/static/images/team/YuanpuLi.jpeg differ