Big data and hydroinformatics

Chen, Yiheng; Han, Dawei

doi:10.2166/hydro.2016.180

Cited by 48 publications

(20 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Large-scale model outputs (e.g., multiple configurations of MODFLOW, Fienen et al, 2018;the National Water Model, Hooper et al, 2017;climate models, Scher, 2018), remote sensing data (e.g., Karpatne et al, 2016;Schaeffer et al, 2018), and hybrid modeled/observed gridded data sets (e.g., NLDAS, Mitchell, 2004) are the "big data" foundation for water resources (Y. Chen & Han, 2016), and the volume of direct in situ observations is small by comparison. Even the "richest" case of observations used in the study presented here included hundreds (not thousands or millions) of daily profiles for training (Figure 2).…”

Section: 1029/2019wr024922mentioning

confidence: 99%

Process‐Guided Deep Learning Predictions of Lake Water Temperature

Read

Jia

Willard

et al. 2019

Water Resources Research

270

207

View full text Add to dashboard Cite

The rapid growth of data in water resources has created new opportunities to accelerate knowledge discovery with the use of advanced deep learning tools. Hybrid models that integrate theory with state‐of‐the art empirical techniques have the potential to improve predictions while remaining true to physical laws. This paper evaluates the Process‐Guided Deep Learning (PGDL) hybrid modeling framework with a use‐case of predicting depth‐specific lake water temperatures. The PGDL model has three primary components: a deep learning model with temporal awareness (long short‐term memory recurrence), theory‐based feedback (model penalties for violating conversation of energy), and model pretraining to initialize the network with synthetic data (water temperature predictions from a process‐based model). In situ water temperatures were used to train the PGDL model, a deep learning (DL) model, and a process‐based (PB) model. Model performance was evaluated in various conditions, including when training data were sparse and when predictions were made outside of the range in the training data set. The PGDL model performance (as measured by root‐mean‐square error (RMSE)) was superior to DL and PB for two detailed study lakes, but only when pretraining data included greater variability than the training period. The PGDL model also performed well when extended to 68 lakes, with a median RMSE of 1.65 °C during the test period (DL: 1.78 °C, PB: 2.03 °C; in a small number of lakes PB or DL models were more accurate). This case‐study demonstrates that integrating scientific knowledge into deep learning tools shows promise for improving predictions of many important environmental variables.

show abstract

Section: 1029/2019wr024922mentioning

confidence: 99%

Process‐Guided Deep Learning Predictions of Lake Water Temperature

Read

Jia

Willard

et al. 2019

Water Resources Research

270

207

View full text Add to dashboard Cite

show abstract

“…In particular, DL can extract the spatio-temporal structure and characteristics of data, and it is a good solution to the problem of strong time dependence such as rainfall simulation and prediction. However, machine learning also has some challenges, such as the cost of big data and interpretability [122,123]. The cost of a big data platform is high, and only when the cost of data collation and cleaning is low can the advantages of big data be maximized.…”

Section: Extending Machine Learning Capabilitiesmentioning

confidence: 99%

A Review on Rainfall Measurement Based on Commercial Microwave Links in Wireless Cellular Networks

Lian

Wei

Sun

et al. 2022

Sensors

View full text Add to dashboard Cite

As one of the most critical elements in the hydrological cycle, real-time and accurate rainfall measurement is of great significance to flood and drought disaster risk assessment and early warning. Using commercial microwave links (CMLs) to conduct rainfall measure is a promising solution due to the advantages of high spatial resolution, low implementation cost, near-surface measurement, and so on. However, because of the temporal and spatial dynamics of rainfall and the atmospheric influence, it is necessary to go through complicated signal processing steps from signal attenuation analysis of a CML to rainfall map. This article first introduces the basic principle and the revolution of CML-based rainfall measurement. Then, the article illustrates different steps of signal process in CML-based rainfall measurement, reviewing the state of the art solutions in each step. In addition, uncertainties and errors involved in each step of signal process as well as their impacts on the accuracy of rainfall measurement are analyzed. Moreover, the article also discusses how machine learning technologies facilitate CML-based rainfall measurement. Additionally, the applications of CML in monitoring phenomena other than rain and the hydrological simulation are summarized. Finally, the challenges and future directions are discussed.

show abstract

“…The access to ARD has transformed how remote sensing is processed for FEWSs. Chen and Han [59] developed a Flood Prevention and Emergency Response System (FPERS) based on GEE. In the preflood stage of the FPERS, a huge amount of geospatial data is integrated into the system and categorized as typhoon forecast and archive, disaster prevention and warning, disaster events, and analysis, or basic data and layers.…”

Section: Progress In Big Data and Cloud Computingmentioning

confidence: 99%

Challenges and Technical Advances in Flood Early Warning Systems (FEWSs)

Perera¹,

Seidou²,

Agnihotri³

et al. 2020

Flood Impact Mitigation and Resilience Enhancement

View full text Add to dashboard Cite

Flood early warning systems (FEWSs)—one of the most common flood-impact mitigation measures—are currently in operation globally. The UN Office for Disaster Risk Reduction (UNDRR) strongly advocates for an increase in their availability to reach the targets of the Sendai Framework for Disaster Risk Reduction and Sustainable Development Goals (SDGs). Comprehensive FEWS consists of four components, which includes (1) risk knowledge, (2) monitoring and forecasting, (3) warning, dissemination, and communication, and (4) response capabilities. Operational FEWSs have varying levels of complexity, depending on available data, adopted technology, and know-how. There are apparent differences in sophistication between FEWSs in developed countries that have the financial capabilities, technological infrastructure, and human resources and developing countries where FEWSs tend to be less advanced. Fortunately, recent advances in remote sensing, artificial intelligence (AI), information technologies, and social media are leading to significant changes in the mechanisms of FEWSs and provide the opportunity for all FEWSs to gain additional capability. These technologies are an opportunity for developing countries to overcome the technical limitations that FEWSs have faced so far. This chapter aims to discuss the challenges in FEWSs in brief and exposes technological advances and their benefits in flood forecasting and disaster mitigation.

show abstract

Big data and hydroinformatics

Cited by 48 publications

References 15 publications

Process‐Guided Deep Learning Predictions of Lake Water Temperature

Process‐Guided Deep Learning Predictions of Lake Water Temperature

A Review on Rainfall Measurement Based on Commercial Microwave Links in Wireless Cellular Networks

Challenges and Technical Advances in Flood Early Warning Systems (FEWSs)

Contact Info

Product

Resources

About