Heterogeneous Stream-reservoir Graph Networks with Data Assimilation
- URL: http://arxiv.org/abs/2110.04959v1
- Date: Mon, 11 Oct 2021 01:47:16 GMT
- Title: Heterogeneous Stream-reservoir Graph Networks with Data Assimilation
- Authors: Shengyu Chen, Alison Appling, Samantha Oliver, Hayley Corson-Dosch,
Jordan Read, Jeffrey Sadler, Jacob Zwart, Xiaowei Jia
- Abstract summary: Accurate prediction of water temperature in streams is critical for monitoring and understanding biogeochemical and ecological processes in streams.
We propose a heterogeneous recurrent graph model to represent interacting processes that underlie stream-reservoir networks.
Because reservoir release data may be unavailable for certain reservoirs, we develop a data assimilation mechanism to correct for the prediction bias caused by reservoir releases.
- Score: 3.312798619476657
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Accurate prediction of water temperature in streams is critical for
monitoring and understanding biogeochemical and ecological processes in
streams. Stream temperature is affected by weather patterns (such as solar
radiation) and water flowing through the stream network. Additionally, stream
temperature can be substantially affected by water releases from man-made
reservoirs to downstream segments. In this paper, we propose a heterogeneous
recurrent graph model to represent these interacting processes that underlie
stream-reservoir networks and improve the prediction of water temperature in
all river segments within a network. Because reservoir release data may be
unavailable for certain reservoirs, we further develop a data assimilation
mechanism to adjust the deep learning model states to correct for the
prediction bias caused by reservoir releases. A well-trained temporal modeling
component is needed in order to use adjusted states to improve future
predictions. Hence, we also introduce a simulation-based pre-training strategy
to enhance the model training. Our evaluation for the Delaware River Basin has
demonstrated the superiority of our proposed method over multiple existing
methods. We have extensively studied the effect of the data assimilation
mechanism under different scenarios. Moreover, we show that the proposed method
using the pre-training strategy can still produce good predictions even with
limited training data.
Related papers
- PostCast: Generalizable Postprocessing for Precipitation Nowcasting via Unsupervised Blurriness Modeling [85.56969895866243]
We propose an unsupervised postprocessing method to eliminate the blurriness without the requirement of training with the pairs of blurry predictions and corresponding ground truth.
A zero-shot blur kernel estimation mechanism and an auto-scale denoise guidance strategy are introduced to adapt the unconditional correlations to any blurriness modes.
arXiv Detail & Related papers (2024-10-08T08:38:23Z) - TransGlow: Attention-augmented Transduction model based on Graph Neural
Networks for Water Flow Forecasting [4.915744683251151]
Hydrometric prediction of water quantity is useful for a variety of applications, including water management, flood forecasting, and flood control.
We propose atemporal forecasting model that augments the hidden state in Graph Convolution Recurrent Neural Network (GCRN) encoder-decoder.
We present a new benchmark dataset of water flow from a network of Canadian stations on rivers, streams, and lakes.
arXiv Detail & Related papers (2023-12-10T18:23:40Z) - An evaluation of deep learning models for predicting water depth
evolution in urban floods [59.31940764426359]
We compare different deep learning models for prediction of water depth at high spatial resolution.
Deep learning models are trained to reproduce the data simulated by the CADDIES cellular-automata flood model.
Our results show that the deep learning models present in general lower errors compared to the other methods.
arXiv Detail & Related papers (2023-02-20T16:08:54Z) - Unsupervised Restoration of Weather-affected Images using Deep Gaussian
Process-based CycleGAN [92.15895515035795]
We describe an approach for supervising deep networks that are based on CycleGAN.
We introduce new losses for training CycleGAN that lead to more effective training, resulting in high-quality reconstructions.
We demonstrate that the proposed method can be effectively applied to different restoration tasks like de-raining, de-hazing and de-snowing.
arXiv Detail & Related papers (2022-04-23T01:30:47Z) - Modeling Reservoir Release Using Pseudo-Prospective Learning and
Physical Simulations to Predict Water Temperature [7.9082555397450225]
This paper proposes a new data-driven method for predicting water temperature in stream networks with reservoirs.
Water flows released from reservoirs greatly affect the water temperature of downstream river segments.
The information of released water flow is often not available for many reservoirs, which makes it difficult for data-driven models to capture the impact to downstream river segments.
arXiv Detail & Related papers (2022-02-11T15:53:50Z) - Assessment of Neural Networks for Stream-Water-Temperature Prediction [0.0]
A mechanistic understanding of the drivers and magnitude of expected changes is essential in identifying system resilience and mitigation measures.
We present a selection of state-of-the-art Neural Networks (NN) for the prediction of water temperatures in six streams in Germany.
arXiv Detail & Related papers (2021-10-08T17:04:42Z) - Back2Future: Leveraging Backfill Dynamics for Improving Real-time
Predictions in Future [73.03458424369657]
In real-time forecasting in public health, data collection is a non-trivial and demanding task.
'Backfill' phenomenon and its effect on model performance has been barely studied in the prior literature.
We formulate a novel problem and neural framework Back2Future that aims to refine a given model's predictions in real-time.
arXiv Detail & Related papers (2021-06-08T14:48:20Z) - Churn Reduction via Distillation [54.5952282395487]
We show an equivalence between training with distillation using the base model as the teacher and training with an explicit constraint on the predictive churn.
We then show that distillation performs strongly for low churn training against a number of recent baselines.
arXiv Detail & Related papers (2021-06-04T18:03:31Z) - Inductive Predictions of Extreme Hydrologic Events in The Wabash River
Watershed [15.963061568077567]
We show that our simple model can be trained much faster than complex attention networks such as GeoMAN.
We also demonstrate that extreme events can be predicted in geographical locations separate from locations observed during the training process.
This spatially-inductive setting enables us to predict extreme events in other areas in the US and other parts of the world using our model trained with the Wabash Basin data.
arXiv Detail & Related papers (2021-04-25T02:26:09Z) - Physics-Guided Recurrent Graph Networks for Predicting Flow and
Temperature in River Networks [3.80455319348953]
We build a recurrent graph network model to capture the interactions among multiple segments in the river network.
We then transfer knowledge from physics-based models to initialize the machine learning model and learn the physics of streamflow and thermodynamics.
We show that the proposed method brings a 33%/14% improvement over the state-of-the-art physics-based model.
arXiv Detail & Related papers (2020-09-26T11:46:51Z) - A Data Scientist's Guide to Streamflow Prediction [55.22219308265945]
We focus on the element of hydrologic rainfall--runoff models and their application to forecast floods and predict streamflow.
This guide aims to help interested data scientists gain an understanding of the problem, the hydrologic concepts involved, and the details that come up along the way.
arXiv Detail & Related papers (2020-06-05T08:04:37Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.