Abstract. This study investigates the ability of long short-term memory (LSTM) neural networks to perform streamflow prediction at ungauged basins. A set of state-of-the-art, hydrological model-dependent regionalization methods are applied to 148 catchments in northeast North America and compared to an LSTM model that uses the exact same available data as the hydrological models. While conceptual model-based methods attempt to derive parameterizations at ungauged sites from other similar or nearby catchments, the LSTM model uses all available data in the region to maximize the information content and increase its robustness. Furthermore, by design, the LSTM does not require explicit definition of hydrological processes and derives its own structure from the provided data. The LSTM networks were able to clearly outperform the hydrological models in a leave-one-out cross-validation regionalization setting on most catchments in the study area, with the LSTM model outperforming the hydrological models in 93 % to 97 % of catchments depending on the hydrological model. Furthermore, for up to 78 % of the catchments, the LSTM model was able to predict streamflow more accurately on pseudo-ungauged catchments than hydrological models calibrated on the target data, showing that the LSTM model's structure was better suited to convert the meteorological data and geophysical descriptors into streamflow than the hydrological models even calibrated to those sites in these cases. Furthermore, the LSTM model robustness was tested by varying its hyperparameters, and still outperformed hydrological models in regionalization in almost all cases. Overall, LSTM networks have the potential to change the regionalization research landscape by providing clear improvement pathways over traditional methods in the field of streamflow prediction in ungauged catchments.


/pdf/continuous-streamflow-prediction-in-ungauged-basins-long-2tivu1hg.pdf

Continuous streamflow prediction in ungauged basins: long short-term memory neural networks clearly outperform traditional hydrological models

Long short-term memory (LSTM) networks have demonstrated their excellent capability in processing long-length temporal dynamics and have proven to be effective in precipitation-runoff modeling. However, the current LSTM hydrological models lack the incorporation of multi-task learning and spatial information, which limits their ability to make full use of meteorological and hydrological data. To address this issue, this study proposes a spatiotemporal deep-learning (DL)-based hydrological model that couples the 2-Dimension convolutional neural network (CNN) and LSTM and introduces actual evaporation (Ea) as an additional training target. The proposed CNN-LSTM model is tested on three large mountainous basins on the Tibetan Plateau, and the results are compared to those obtained from the LSTM-only model. Additionally, a probe method is used to decipher the internal embedding layers of the proposed DL models. The results indicate that both LSTM and CNN-LSTM hydrological models perform well in simulating runoff (Q) and Ea, with Nash-Sutcliffe efficiency coefficients (NSEs) higher than 0.82 and 0.95, respectively. The higher NSEs suggest that introducing spatial information into LSTM-only models can improve the overall and peak model performance. Moreover, multi-task simulation with LSTM-only models shows better accuracy in the estimation of Q volume and performance, with NSEs increasing by approximately 0.02. The probe method also reveals that CNN can capture the basin-averaged meteorological values in CNN-LSTM models, while LSTM Q (Ea) models contain the information about the known Ea (Q) process. Overall, this study demonstrates the value of spatial information and multi-task learning in LSTM hydrological modeling and provides a perspective for interpreting the internal embedding layers of DL models. 

Improving LSTM hydrological modeling with spatiotemporal deep learning and multi-task learning: a case study of three mountainous areas on the Tibetan Plateau

Since 1880, the Earth's temperature has increased at a pace of 0.14° Fahrenheit (0.08° Celsius) every decade; however, the rate of warming since 1981 is more than double that, at 0.32 °F (0.18 °C) per decade. Based on NOAA's temperature data, 2021 was the sixth hottest year on record. Warmer temperatures can also lead to a chain reaction of other global changes. That's because increasing air temperature affects the oceans, weather patterns, snow and ice, and plants and animals. The warmer it gets, the more severe the effects on people and the environment. The global average surface temperature has risen at an average rate of 0.17 °F per decade since 1901. The Global Surface Temperature Change data recorded by the National Aeronautics and Space Administration Goddard Institute for Space Studies (NASA-GISS) was used in this paper. This article attempted to design a model for Time Series Data from 1961 to 2020 for Global Temperature Change Prediction with the help of machine learning algorithms. Therefore, Extra Trees, light gradient boosting machine, Random Forest, K nearest neighbors, gradient boosting, and Bayesian ridge algorithms were investigated to create a Global Temperature Change Prediction Model and the evaluation criteria such as MAE (C°), MSE (C°), RMSE (C°), R2 and RMSLE (C °) and MAPE (C °) were calculated, and also the execution time of the algorithms was obtained in seconds. The obtained results showed that the Extra Trees algorithm has the best performance in predicting Global Temperature Change. 

Utilizing time series data from 1961 to 2019 recorded around the world and machine learning to create a Global Temperature Change Prediction Model

Iterative integration of deep learning in hybrid Earth surface system modelling

Urban pluvial flooding (UPF) resulting from localized, intense, rainfall-generated ponding and overland flow causes a range of socio-environmental impacts. UPF is driven by a complex set of interconnected factors, including physical, historical, social, cultural, institutional, and economic conditions. Its impacts are increasing due to both biophysical change (e.g., global warming) and the interactions between the human and physical dimensions of the urban environment (e.g., land-use change). Notwithstanding its complexity and the rather low level of attention it has received in both research and practice, UPF is an issue that needs to be tackled from a comprehensive perspective. Different integrated approaches such as citizen science and socio-hydrology have tried to address UPF by coupling humans and environmental systems, reflecting the possible outcomes from the interaction between disciplines—albeit not without limitations. This paper presents findings on a review of current integrated community-based approaches to UPF research and discusses how scholars have approached this problem and its management. The limitations of these approaches to fully capture the multi-dimensional nature of UPF are explored in detail, and research gaps are identified. Finally, the paper provides suggestions for future research based on a transdisciplinary, transformative citizen science approach. 

Integrated community-based approaches to urban pluvial flooding research, trends and future directions: A review

/pdf/evaluation-of-machine-learning-methods-application-in-1ji3ojmn.pdf

Evaluation of Machine Learning Methods Application in Temperature Prediction

This study considers the optimum design of reinforced concrete combined footings. Analysis and design procedures are developed based on the American Concrete Institute (ACI 318-05) regulations and several geotechnical considerations for providing stability to the structure. Low-cost designs are generated using five swarm intelligence algorithms [i.e., particle swarm optimization (PSO), accelerated particle swarm optimization (APSO), whale optimization algorithm (WOA), ant lion optimizer (ALO), and moth flame optimization (MFO)]. The performance of these algorithms is examined through two numerical simulations. First, a combined footing design from the literature is optimized using the five swarm intelligence algorithms. The impacts of concrete compressive strength (fc) on the final cost are studied through a sensitivity analysis. Second, rectangular and trapezoidal combined footings are optimized using the best algorithm in the first example (i.e., PSO) to explore the effect of shape on the final design. Also, a sensitivity analysis is performed on the effects of the design parameters on the cost. 

Optimum design of combined footings using swarm intelligence-based algorithms

Modeling of Local Scour Depth Around Bridge Pier Using FLOW 3D

Piano Key Weirs have recently been used as new or rehabilitation options in the world because of their advantages in hydraulic performance and construction costs. However, designing an efficient PKW is challenging due to a large and complex set of geometric and hydraulic parameters. Therefore, reaching an optimal PKW design depends on the examination of various geometric combinations and hydraulic parameters. In this study, we applied a multi-objective optimization model known as Non-dominated Sorting Genetic Algorithm-II to determine an optimal design by maximizing hydraulic discharge while minimizing the volume of the concrete. Here, we evaluated the capability of our approach in two separate case studies, one which represented as a rehabilitated weir and one as a new design. Both studies show that the developed approach could significantly reduce the concrete volume per unit of discharge. Moreover, the results show similar patterns in terms of the hydro-economic behavior of the model.

Application of a multi-objective optimization model for the design of piano key weirs with a fixed dam height

Given the significant momentum of developing water quality models to simulate water quality variables and support decision-making, the literature recognizes the importance of addressing uncertainties embedded in the water quality models, such as inherent, parametric, and hydrological uncertainties. However, previous studies have not extensively examined the magnitude of hydrological events in terms of their intensity. Therefore, this paper aims to propose an adjusted Monte Carlo event-based scenarios framework that considers four scenarios (1- 35 years of flow rate records, 2- events with ARI ≤ 10 years, 3- events with ARI ≤ 5 years, 4- events with ARI ≤ 1) to evaluate hydrological variabilities and quantify embedded uncertainties. The study employs a Qual2k model that simulates five water quality variables in the Zaroub River, Iran, as a case study. The model’s uncertainty boundaries are quantified using five statistical metrics: Plevel, ARIL, SU, CU, and EU. The study’s findings reveal that when considering the flow rate time histories during extreme hydrological events, there is a significant increase in uncertainty in the water quality model, highlighting the challenge of incorporating various scenarios within the framework such as high computational demand, integrating different scenarios, sparse data, and its temporal resolution. On the other hand, reducing the ARI values of hydrological events not only minimizes the uncertainty boundaries but also improves the accuracy of the model simulations. These results underscore the critical importance of selecting hydrological scenarios based on the water quality variable under investigation. Furthermore, the proposed framework can be applied to any water quality model and water body. The study’s outcomes suggest that the presented methodology reduces uncertainty and provides more reliable simulations for decision-making in water resources conundrums.

Evaluation of hydrological variabilities of water quality models considering event-based scenarios: A case study

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Saman Ebrahimi

Author Tools

Chat about Author