Our work on TFT for streamflow prediction is now published in the Journal of Hydrology! Combining attention mechanisms with recurrent networks enhances streamflow prediction (in 2,610 basins worldwide), compared to either approach alone. https://t.co/KQYVOOMH0D
@Tirthankar__Roy
Inside WaterResearch - Issue 19:
Dive into the performance of various models on the #GreatLakes—a region with complex transboundary datasets, diverse climatic and land use conditions, and immense socio-economic importance to both the USA and Canada.
https://t.co/mSbiR0T2Su
The last three days at #HydroML were incredible! I had the chance to connect with so many bright & beautiful minds, present my latest work, and engage in fantastic discussions. Above all, I feel amazing for being part of such a wonderful community. Thank you @PNNLab
Please apply and share with those who my be interested.
Dates for Summer School are July 1 to 21, 2024.
The deadline for applications is extended to June 7, 2024.
Application link: https://t.co/5T0W1llbTS #RemoteSensing#GIS#GeospatialTechnology
Looking forward to the 3rd HydroML Symposium! Let's take our ML skills to the next level. Join us to refine and polish your abilities. #HydroML#MLSymposium
The best place to relax is near water.
After just 2 minutes of viewing water outdoors, blood pressure and heart rate drop. It's more calming to look at a lake, pool, or stream than trees or grass.
Beaches are popular for a reason. Wider bodies of water bring more tranquility.
Our work on TFT for streamflow prediction is now published in the Journal of Hydrology! Combining attention mechanisms with recurrent networks enhances streamflow prediction (in 2,610 basins worldwide), compared to either approach alone. https://t.co/KQYVOOMH0D
@Tirthankar__Roy
@EhsanForoumandi@GavahiKeyhan@HamidMoradkhani@theAGU We recently implemented an auto-encoder based framework for snow droughts. Combined with Mutual Information, the method determine the weights of inputs. If interest, here is the link https://t.co/nLnqYJE4Y0
▶️A causal link exists between the North-Pacific index, which measures #sea-level pressure in the Northern #Pacific Ocean, and the frequency of rain-on-snow events in North America.
@rk_sinan @KanakKantiKar @Tirthankar__Roy
🔗Read more: https://t.co/kxZ5jia7b1
It was a great experience giving a talk on Streamflow Forecasting with Temporal Fusion Transformers in AGU23 Conference in San Fransisco.
If you are interested, find more in our preprint here: https://t.co/y9TPRXphCU
@theAGU#AGU23
Water and Climate Lab family @theAGU fall meeting in San Francisco! Unfortunately, I have missed it. These young researchers are having a wonderful time! #AGU2023#AGU23
We (Students of Roy Research Group) are/will be presenting our ongoing work @theAGU from @unl_cee. If you are attending #AGU23, you are cordially invited in our presentations.
@rk_sinan@Tirthankar__Roy
Thrilled to share our recent work showing that combining attention with recurrence can improve streamflow prediction. For the first time, we set up Temporal Fusion Transformers for 2610 basins worldwide. TFTs outperform benchmark LSTMs & Transformers.
https://t.co/y9TPRXoJNm
Our new work, “Applicability of a Flood Forecasting System for Nebraska Watersheds,” published in EMS. This work is an important stepping stone towards a statewide operational real-time flood forecasting system for Nebraska. https://t.co/xFT6pdVj26