Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: A Transdisciplinary Review of Deep Learning Research and Its Relevance for Water Resources Scientists

Journal Article · · Water Resources Research
ORCiD logo [1]
  1. Civil and Environmental EngineeringPennsylvania State University University Park PA USA
+ Show Author Affiliations

Deep learning (DL), a new generation of artificial neural network research, has transformed industries, daily lives, and various scientific disciplines in recent years. DL represents significant progress in the ability of neural networks to automatically engineer problem-relevant features and capture highly complex data distributions. I argue that DL can help address several major new and old challenges facing research in water sciences such as interdisciplinarity, data discoverability, hydrologic scaling, equifinality, and needs for parameter regionalization. This review paper is intended to provide water resources scientists and hydrologists in particular with a simple technical overview, transdisciplinary progress update, and a source of inspiration about the relevance of DL to water. The review reveals that various physical and geoscientific disciplines have utilized DL to address data challenges, improve efficiency, and gain scientific insights. DL is especially suited for information extraction from image-like data and sequential data. Techniques and experiences presented in other disciplines are of high relevance to water research. Meanwhile, less noticed is that DL may also serve as a scientific exploratory tool. A new area termed AI neuroscience , where scientists interpret the decision process of deep networks and derive insights, has been born. This budding subdiscipline has demonstrated methods including correlation-based analysis, inversion of network-extracted features, reduced-order approximations by interpretable models, and attribution of network decisions to inputs. Moreover, DL can also use data to condition neurons that mimic problem-specific fundamental organizing units, thus revealing emergent behaviors of these units. Vast opportunities exist for DL to propel advances in water sciences.

Research Organization:
Univ. of California, Davis, CA (United States)
Sponsoring Organization:
National Science Foundation (NSF); USDOE Office of Science (SC)
Grant/Contract Number:
SC0016605
OSTI ID:
1480877
Journal Information:
Water Resources Research, Journal Name: Water Resources Research Journal Issue: 11 Vol. 54; ISSN 0043-1397
Publisher:
American Geophysical Union (AGU)Copyright Statement
Country of Publication:
United States
Language:
English

References (194)

Elements of Information Theory book January 1991
Surface-subsurface model intercomparison: A first set of benchmark results to diagnose integrated hydrology and feedbacks journal February 2014
Nonparametric estimation of groundwater residence time distributions: What can environmental tracer data tell us about groundwater residence time? journal March 2014
Toward the camera rain gauge journal March 2015
Catchment coevolution: A useful framework for improving predictions of hydrological change? journal July 2015
Improving the representation of hydrologic processes in Earth System Models: REPRESENTING HYDROLOGIC PROCESSES IN EARTH SYSTEM MODELS journal August 2015
A unified approach for process‐based hydrologic modeling: 1. Modeling concept journal April 2015
The fan of influence of streams and channel feedbacks to simulated land surface water and carbon dynamics: CHANNEL FEEDBACKS TO SIMULATED LAND SURFACE DYNAMICS journal February 2016
Global-scale regionalization of hydrologic model parameters: GLOBAL-SCALE REGIONALIZATION journal May 2016
Full-flow-regime storage-streamflow correlation patterns provide insights into hydrologic functioning over the continental US: STORAGE-STREAMFLOW CORRELATION SPECTRUM journal September 2017
Prolongation of SMAP to Spatiotemporally Seamless Coverage of Continental U.S. Using a Deep Learning Neural Network journal November 2017
Doing ecohydrology backward: Inferring wetland flow and hydroperiod from landscape patterns: DOING ECOHYDROLOGY BACKWARD journal July 2017
The Growth of Hydrological Understanding: Technologies, Ideas, and Societal Needs Shape the Field: GROWTH OF HYDROLOGICAL UNDERSTANDING journal October 2017
Training‐Image Based Geostatistical Inversion Using a Spatial Generative Adversarial Neural Network journal January 2018
Deep learning with convolutional neural networks for EEG decoding and visualization: Convolutional Neural Networks in EEG Analysis journal August 2017
Efficacy of neural network and genetic algorithm techniques in simulating spatio-temporal fluctuations of groundwater: NEURAL NETWORK AND GENETIC ALGORITHM FOR GROUNDWATER LEVEL SIMULATION journal March 2014
Scale issues in hydrological modelling: A review journal April 1995
Genetic programming approach for flood routing in natural channels journal January 2008
Prediction of hourly actual evapotranspiration using neural networks, genetic programming, and statistical models journal July 2010
Predicting backbone Cα angles and dihedrals from protein sequences by stacked sparse auto-encoder deep neural network journal September 2014
Deep learning for computational chemistry journal March 2017
Classification and regression trees: Classification and regression trees journal January 2011
Estimating epistemic and aleatory uncertainties during hydrologic modeling: An information theoretic approach: ESTIMATING EPISTEMIC AND ALEATORY UNCERTAINTIES journal April 2013
Visualizing and Understanding Convolutional Networks book January 2014
Unsupervised Learning book January 2004
Support-vector networks journal September 1995
Deep learning in color: towards automated quark/gluon jet discrimination journal January 2017
Jet-images — deep learning edition journal July 2016
On Early Stopping in Gradient Descent Learning journal April 2007
Downscaling GCMs using the Smooth Support Vector Machine method to predict daily precipitation in the Hanjiang Basin journal February 2010
A Computational Intelligence-Based Genetic Programming Approach for the Simulation of Soil Water Retention Curves journal May 2014
Linear genetic programming for time-series modelling of daily flow rate journal April 2009
A deep learning approach for human behavior prediction with explanations in health social networks: social restricted Boltzmann machine (SRBM+) journal September 2016
Modeling spatio-temporal distribution of soil moisture by deep learning-based cellular automata model journal May 2016
Genetic programming based monthly groundwater level forecast models with uncertainty quantification journal January 2016
Multilayer feedforward networks are universal approximators journal January 1989
rosetta : a computer program for estimating soil hydraulic parameters with hierarchical pedotransfer functions journal October 2001
Real time wave forecasting using neural networks journal August 1998
The effect of internal parameters and geometry on the performance of back-propagation neural networks: an empirical study journal April 1998
Comparison of Regularization Methods for ImageNet Classification with Deep Convolutional Neural Networks journal January 2014
Estimating soil moisture using remote sensing data: A machine learning approach journal January 2010
Inversion using a new low-dimensional representation of complex binary geological media based on a deep neural network journal December 2017
Understanding and managing the food-energy-water nexus – opportunities for water resources research journal January 2018
The dropout learning algorithm journal May 2014
Support vector machine applications in the field of hydrology: A review journal June 2014
Data-driven methods to improve baseflow prediction of a regional groundwater model journal December 2015
The introspective may achieve more: Enhancing existing Geoscientific models with native-language emulated structural reflection journal January 2018
Downstream sedimentary and geomorphic impacts of the Three Gorges Dam on the Yangtze River journal November 2014
Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions journal August 2010
Uncertainty analysis of a semi-distributed hydrologic model based on a Gaussian Process emulator journal March 2018
POLARIS: A 30-meter probabilistic soil series map of the contiguous United States journal July 2016
Change detection based on deep feature representation and mapping transformation for multi-spatial-resolution remote sensing images journal June 2016
Biclustering on expression data: A review journal October 2015
Prediction and simulation of monthly groundwater levels by genetic programming journal December 2013
Input determination for neural network models in water resources applications. Part 2. Case study: forecasting salinity in a river journal January 2005
Multi-time scale stream flow predictions: The support vector machines approach journal March 2006
A manifesto for the equifinality thesis journal March 2006
Support vector regression for real-time flood stage forecasting journal September 2006
Downscaling of precipitation for climate change scenarios: A support vector machine approach journal November 2006
Short-term streamflow forecasting with global climate change implications – A comparative study between genetic programming and neural network models journal May 2008
A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series journal August 2009
A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer journal January 2011
SVM, ANFIS, regression and climate based models for reference evapotranspiration modeling using limited climatic data in a semi-arid highland environment journal June 2012
Insights from socio-hydrology modelling on dealing with flood risk – Roles of collective memory, risk-taking attitude and trust journal October 2014
Monthly streamflow forecasting using Gaussian Process Regression journal April 2014
Artificial intelligence based models for stream-flow forecasting: 2000–2015 journal November 2015
Daily reservoir inflow forecasting using multiscale deep feature learning with hybrid models journal January 2016
An overview of current applications, challenges, and future trends in distributed process-based models in hydrology journal June 2016
Estimating a-priori kinematic wave model parameters based on regionalization for flash flood forecasting in the Conterminous United States journal October 2016
Use long short-term memory to enhance Internet of Things for combined sewer overflow monitoring journal January 2018
Deep learning in neural networks: An overview journal January 2015
Towards better exploiting convolutional neural networks for remote sensing scene classification journal January 2017
Geological Disaster Recognition on Optical Remote Sensing Images Using Deep Learning journal January 2016
A data mining approach for understanding topographic control on climate-induced inter-annual vegetation variability over the United States journal September 2005
Soil moisture retrieval from AMSR-E and ASCAT microwave observation synergy. Part 2: Product evaluation journal June 2017
A data-mining framework for exploring the multi-relation between fish species and water quality through self-organizing map journal February 2017
Deep learning for studies of galaxy morphology journal October 2016
Computational Modeling of β-Secretase 1 (BACE-1) Inhibitors Using Ligand Based Approaches journal October 2016
Convolutional Embedding of Attributed Molecular Graphs for Physical Property Prediction journal July 2017
Deep Architectures and Deep Learning in Chemoinformatics: The Prediction of Aqueous Solubility for Drug-Like Molecules journal July 2013
A new neural network approach including first guess for retrieval of atmospheric water vapor, cloud liquid water path, surface temperature, and emissivities over land from satellite microwave observations journal July 2001
Self-organizing linear output map (SOLO): An artificial neural network suitable for hydrologic modeling and analysis: SOLO, AN ANN MODEL SUITABLE FOR HYDROLOGIC MODELING journal December 2002
Characterization of footprint-scale surface soil moisture variability using Gaussian and beta distribution functions during the Southern Great Plains 1997 (SGP97) hydrology experiment: FOOTPRINT-SCALE SURFACE SOIL MOISTURE journal December 2005
An efficient calibration method for continental-scale land surface modeling: EFFICIENT CALIBRATION FOR LARGE-SCALE LAND SURFACE MODELING journal September 2008
Catchments as simple dynamical systems: Catchment characterization, rainfall-runoff modeling, and doing hydrology backward: CATCHMENTS AS SIMPLE DYNAMICAL SYSTEMS journal February 2009
The future of hydrology: An evolving science for a changing world: OPINION journal May 2010
Hyperresolution global land surface modeling: Meeting a grand challenge for monitoring Earth's terrestrial water: OPINION journal May 2011
Daily spatiotemporal precipitation simulation using latent and transformed Gaussian processes: PRECIPITATION SIMULATION USING GAUSSIAN PROCESSES journal January 2012
The Use of Artificial Neural Networks for the Prediction of Water Quality Parameters journal April 1996
Learning representations by back-propagating errors journal October 1986
Deep learning journal May 2015
Mastering the game of Go with deep neural networks and tree search journal January 2016
Fast automated analysis of strong gravitational lenses with convolutional neural networks journal August 2017
Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning journal July 2015
Deep learning for regulatory genomics journal August 2015
Quantum-chemical insights from deep tensor neural networks journal January 2017
Searching for exotic particles in high-energy physics with deep learning journal July 2014
Depletion and response of deep groundwater to climate-induced pumping variability journal January 2017
Improving prediction of secondary structure, local backbone angles and solvent accessible surface area of proteins by iterative deep learning journal June 2015
Application of Support Vector Machine in Lake Water Level Prediction journal May 2006
SchNet – A deep learning architecture for molecules and materials journal June 2018
Unreasonable effectiveness of learning neural networks: From accessible states and robust ensembles to basic algorithmic schemes journal November 2016
Hydrologic regulation of plant rooting depth journal September 2017
Direct Clustering of a Data Matrix journal March 1972
Image Processing, Computer Vision, and Deep Learning: new approaches to the analysis and physics interpretation of LHC events journal October 2016
A convolutional neural network neutrino event classifier journal September 2016
Deep learning in bioinformatics journal July 2016
Enhanced Higgs Boson to τ + τ − Search with Deep Learning journal March 2015
Model-Free Prediction of Large Spatiotemporally Chaotic Systems from Data: A Reservoir Computing Approach journal January 2018
Backpropagation through time: what it does and how to do it journal January 1990
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey journal January 2018
Gaussian process based spatial modeling of soil moisture for dense soil moisture sensing network conference August 2017
A Deep-Learning Based Precipitation Forecasting Approach Using Multiple Environmental Factors conference June 2017
Unsupervised Learning of Invariant Feature Hierarchies with Applications to Object Recognition conference June 2007
Pedestrian Detection with Unsupervised Multi-stage Feature Learning conference June 2013
Going deeper with convolutions conference June 2015
A Dynamic Convolutional Layer for short rangeweather prediction conference June 2015
Understanding deep image representations by inverting them conference June 2015
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network conference July 2017
Plug & Play Generative Networks: Conditional Iterative Generation of Images in Latent Space conference July 2017
Monitoring Ethiopian Wheat Fungus with Satellite Imagery and Deep Feature Learning conference July 2017
Speech recognition with deep recurrent neural networks conference May 2013
Robust Speech Recognition Using Generative Adversarial Networks conference April 2018
DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving conference December 2015
Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks conference October 2017
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era conference October 2017
Face aging with conditional generative adversarial networks conference September 2017
Revealing Fundamental Physics from the Daya Bay Neutrino Experiment Using Deep Neural Networks conference December 2016
Soil moisture retrieval from SMOS observations using neural networks
  • Rodriguez-Fernandez, N.; Richaume, P.; Aires, F.
  • IGARSS 2014 - 2014 IEEE International Geoscience and Remote Sensing Symposium, 2014 IEEE Geoscience and Remote Sensing Symposium https://doi.org/10.1109/IGARSS.2014.6946963
conference July 2014
Estimating crop yields with deep learning and remotely sensed data
  • Kuwata, Kentaro; Shibasaki, Ryosuke
  • IGARSS 2015 - 2015 IEEE International Geoscience and Remote Sensing Symposium, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) https://doi.org/10.1109/IGARSS.2015.7325900
conference July 2015
Deep supervised learning for hyperspectral data classification through convolutional neural networks conference July 2015
Modeling Urbanization Patterns with Generative Adversarial Networks conference July 2018
The Soil Moisture Active Passive (SMAP) Mission journal May 2010
Vehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural Networks journal October 2014
High-Resolution SAR Image Classification via Deep Convolutional Autoencoders journal November 2015
Deep Learning Earth Observation Classification Using ImageNet Pretrained Networks journal January 2016
Convolutional Neural Network With Data Augmentation for SAR Target Recognition journal January 2016
Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art journal June 2016
Crafting adversarial input sequences for recurrent neural networks conference November 2016
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups journal November 2012
Generative Adversarial Networks: An Overview journal January 2018
Deep learning with convolutional neural networks for decoding and visualization of EEG pathology conference December 2017
A new look at the statistical model identification journal December 1974
SAR ATR by a combination of convolutional neural network and support vector machines journal December 2016
A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction journal January 2015
Sea Ice Concentration Estimation During Melt From Dual-Pol SAR Scenes Using Deep Convolutional Neural Networks: A Case Study journal August 2016
Deep Recurrent Neural Networks for Hyperspectral Image Classification journal July 2017
Accurate Object Localization in Remote Sensing Images Based on Convolutional Neural Networks journal May 2017
NeC4.5: neural ensemble based C4.5 journal June 2004
Theory-Guided Data Science: A New Paradigm for Scientific Discovery from Data journal October 2017
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning journal May 2016
Guest Editorial Deep Learning in Medical Imaging: Overview and Future Promise of an Exciting New Technique journal May 2016
Evaluating the Visualization of What a Deep Neural Network Has Learned journal November 2017
Representation Learning: A Review and New Perspectives journal August 2013
Understanding Hidden Memories of Recurrent Neural Networks conference October 2017
How Much Chemistry Does a Deep Neural Network Need to Know to Make Accurate Predictions? conference March 2018
Reducing the Dimensionality of Data with Neural Networks journal July 2006
The AI detectives journal July 2017
The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions journal April 1998
Extracting and composing robust features with denoising autoencoders conference January 2008
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
  • Ribeiro, Marco Tulio; Singh, Sameer; Guestrin, Carlos
  • Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '16 https://doi.org/10.1145/2939672.2939778
conference January 2016
GPUs reshape computing journal August 2016
DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution
  • Vandal, Thomas; Kodra, Evan; Ganguly, Sangram
  • Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '17 https://doi.org/10.1145/3097983.3098004
conference January 2017
Redundancy Reduction as a Strategy for Unsupervised Learning journal March 1993
Long Short-Term Memory journal November 1997
A Fast Learning Algorithm for Deep Belief Nets journal July 2006
Evaluation of PERSIANN System Satellite–Based Estimates of Tropical Rainfall journal September 2000
Bias Adjustment of Satellite Precipitation Estimation Using Ground-Based Measurement: A Case Study Evaluation over the Southwestern United States journal October 2009
Precipitation Estimation from Remotely Sensed Imagery Using an Artificial Neural Network Cloud Classification System journal December 2004
Benchmarking NLDAS-2 Soil Moisture and Evapotranspiration to Separate Uncertainty Contributions journal March 2016
A Deep Neural Network Modeling Framework to Reduce Bias in Satellite Precipitation Products journal March 2016
Precipitation Identification with Bispectral Satellite Information Using Deep Learning Approaches journal May 2017
Neural Error Regression Diagnosis (NERD): A Tool for Model Bias Identification and Prognostic Data Assimilation journal February 2006
Systematic Bias in Land Surface Models journal October 2007
Hydrological modelling using artificial neural networks journal March 2001
Handbook of Markov Chain Monte Carlo book May 2011
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation journal July 2015
Deep learning for computational biology journal July 2016
Deep Gaussian Process for Crop Yield Prediction Based on Remote Sensing Data journal February 2017
Using support vector machines for long-term discharge prediction journal August 2006
Estimation of daily suspended sediments using support vector machines journal June 2008
A Method for Scaling Vegetation Dynamics: the Ecosystem Demography Model (ed) journal November 2001
Estimating Saturated Hydraulic Conductivity Using Genetic Programming journal January 2007
Deep-learned Top Tagging with a Lorentz Layer journal January 2018
Rainfall and runoff forecasting with SSA–SVM approach journal July 2001
Deep Convolutional Neural Networks for Forest Fire Detection conference January 2016
DeepTox: Toxicity Prediction using Deep Learning journal February 2016
Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery journal November 2015
Socio-hydrology: conceptualising human-flood interactions journal January 2013
Socio-hydrologic drivers of the pendulum swing between agricultural development and environmental health: a case study from Murrumbidgee River basin, Australia journal January 2014
A prototype framework for models of socio-hydrology: identification of key feedback loops and parameterisation approach journal January 2014
Characterizing hydrologic change through catchment classification journal January 2014
The future of Earth observation in hydrology journal January 2017
Toward enhanced understanding and projections of climate extremes using physics-guided data mining techniques journal January 2014

Similar Records

Related Subjects

54 ENVIRONMENTAL SCIENCES
59 BASIC BIOLOGICAL SCIENCES
AI neuroscience
artificial intelligence
data mining
deep learning
environmental sciences & ecology
marine & freshwater biology
transformative
water resources