HydroDeep -- A Knowledge Guided Deep Neural Network for Geo-Spatiotemporal Data Analysis

• URL: http://arxiv.org/abs/2010.04328v2
• Date: Mon, 8 Feb 2021 20:47:24 GMT
• Title: HydroDeep -- A Knowledge Guided Deep Neural Network for Geo-Spatiotemporal Data Analysis
• Authors: Aishwarya Sarkar, Jien Zhang, Chaoqun Lu, Ali Jannesari
• Abstract summary: This paper demonstrates a hybrid neural network architecture - HydroDeep. It couples a process-based hydro-ecological model with a combination of Deep Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) Network. It outperforms the independent CNN's and LSTM's performance by 1.6% and 10.5% respectively in Nash-Sutcliffe efficiency.
• Score: 0.726437825413781
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Due to limited evidence and complex causes of regional climate change, the confidence in predicting fluvial floods remains low. Understanding the fundamental mechanisms intrinsic to geo-spatiotemporal information is crucial to improve the prediction accuracy. This paper demonstrates a hybrid neural network architecture - HydroDeep, that couples a process-based hydro-ecological model with a combination of Deep Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) Network. HydroDeep outperforms the independent CNN's and LSTM's performance by 1.6% and 10.5% respectively in Nash-Sutcliffe efficiency. Also, we show that HydroDeep pre-trained in one region is adept at passing on its knowledge to distant places via unique transfer learning approaches that minimize HydroDeep's training duration for a new region by learning its regional geo-spatiotemporal features in a reduced number of iterations.

Related papers

• GeoFUSE: A High-Efficiency Surrogate Model for Seawater Intrusion Prediction and Uncertainty Reduction [0.10923877073891446]
  Seawater intrusion into coastal aquifers poses a significant threat to groundwater resources. We develop GeoFUSE, a novel deep-learning-based surrogate framework. We apply GeoFUSE to a 2D cross-section of the Beaver Creek tidal stream-floodplain system in Washington State.
  arXiv  Detail & Related papers  (2024-10-26T08:10:32Z)
• Long-term drought prediction using deep neural networks based on geospatial weather data [75.38539438000072]
  High-quality drought forecasting up to a year in advance is critical for agriculture planning and insurance. We tackle drought data by introducing an end-to-end approach that adopts a systematic end-to-end approach. Key findings are the exceptional performance of a Transformer model, EarthFormer, in making accurate short-term (up to six months) forecasts.
  arXiv  Detail & Related papers  (2023-09-12T13:28:06Z)
• Exploring Geometric Deep Learning For Precipitation Nowcasting [28.44612565923532]
  We propose a geometric deep learning-based temporal Graph Convolutional Network (GCN) for precipitation nowcasting. The adjacency matrix that simulates the interactions among grid cells is learned automatically by minimizing the L1 loss between prediction and ground truth pixel value. We test the model on sequences of radar reflectivity maps over the Trento/Italy area.
  arXiv  Detail & Related papers  (2023-09-11T21:14:55Z)
• Speed Limits for Deep Learning [67.69149326107103]
  Recent advancement in thermodynamics allows bounding the speed at which one can go from the initial weight distribution to the final distribution of the fully trained network. We provide analytical expressions for these speed limits for linear and linearizable neural networks. Remarkably, given some plausible scaling assumptions on the NTK spectra and spectral decomposition of the labels -- learning is optimal in a scaling sense.
  arXiv  Detail & Related papers  (2023-07-27T06:59:46Z)
• 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)
• Accelerating Domain-aware Deep Learning Models with Distributed Training [0.8164433158925593]
  We present a novel distributed domain-aware network that utilizes domain-specific knowledge with improved model performance. From our analysis, the network effectively predicts high peaks in discharge measurements at watershed outlets with up to 4.1x speedup. Our approach achieved a 12.6x overall speedup and the mean prediction performance by 16%.
  arXiv  Detail & Related papers  (2023-01-25T22:59:47Z)
• Transfer Learning Approaches for Knowledge Discovery in Grid-based Geo-Spatiotemporal Data [1.2693545159861856]
  Extracting and analyzing geo-spatiotemporal features is crucial to recognize underlying causes of natural, events such as floods. We propose HydroDeep, an effectively reusable pretrained model to address this problem of transferring knowledge from one region to another.
  arXiv  Detail & Related papers  (2021-10-02T16:55:34Z)
• Probabilistic modeling of lake surface water temperature using a Bayesian spatio-temporal graph convolutional neural network [55.41644538483948]
  We propose to aggregate simulations of lake temperature at a certain depth together with a range of meteorological features. This work demonstrates that the proposed model can deliver homogeneously good performance covering the whole lake surface. Results are compared with a state-of-the-art Bayesian deep learning method.
  arXiv  Detail & Related papers  (2021-09-27T09:19:53Z)
• Learning to Estimate RIS-Aided mmWave Channels [50.15279409856091]
  We focus on uplink cascaded channel estimation, where known and fixed base station combining and RIS phase control matrices are considered for collecting observations. To boost the estimation performance and reduce the training overhead, the inherent channel sparsity of mmWave channels is leveraged in the deep unfolding method. It is verified that the proposed deep unfolding network architecture can outperform the least squares (LS) method with a relatively smaller training overhead and online computational complexity.
  arXiv  Detail & Related papers  (2021-07-27T06:57:56Z)
• KNN, An Underestimated Model for Regional Rainfall Forecasting [6.421670116083633]
  This paper aims to design an integrated tool by applying various machine learning algorithms. Deep Neural Network, Wide Neural Network, Deep and Wide Neural Network, Reservoir Computing, Long Short Term Memory, Support Vector Machine, K-Nearest Neighbor for forecasting regional precipitations over different catchments in Upstate New York.
  arXiv  Detail & Related papers  (2021-03-28T22:25:29Z)
• Rectified Linear Postsynaptic Potential Function for Backpropagation in Deep Spiking Neural Networks [55.0627904986664]
  Spiking Neural Networks (SNNs) usetemporal spike patterns to represent and transmit information, which is not only biologically realistic but also suitable for ultra-low-power event-driven neuromorphic implementation. This paper investigates the contribution of spike timing dynamics to information encoding, synaptic plasticity and decision making, providing a new perspective to design of future DeepSNNs and neuromorphic hardware systems.
  arXiv  Detail & Related papers  (2020-03-26T11:13:07Z)

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.