Development of risk assessment model for groundwater level by wavelet-deep learning approach with smart pumping data

Mapping Intimacies ◽

10.5194/egusphere-egu21-4624 ◽

2021 ◽

Author(s):

Tsai-Ning Weng ◽

Chu-Chun Hsu ◽

Yuan-Chien Lin

Keyword(s):

Risk Assessment ◽

Deep Learning ◽

Wavelet Transform ◽

Water Level ◽

Groundwater Level ◽

Groundwater Resources ◽

Assessment Model ◽

Small Scale ◽

Time Lags ◽

Learning Models

AbstractGroundwater, as a vital existence in human life and economic development, is also one of the stable sources of water resources. Therefore, how to properly utilize groundwater becomes a very important issue when faced with water shortages. However, most of the previous literature uses monthly data as the time scale, and usually uses the historical water level data of the area as the only input factor in the modeling process without considering pumping information and rainfall. This shows that the current studies of small-scale data which is based on the use of multiple factors with hydrological mechanisms to explore and predict the groundwater level is still quite lacking.Therefore, this study proposed a novel framework combining wavelet analysis and deep learning models called wavelet-deep learning models and taking the Daliao area of &#8203;&#8203;Kaohsiung as an example. From the historical hourly observation data during 2017/08/23-2020/01/30, including groundwater level, smart pumping measurement, tidal, and meteorological data. After abstracting important features of each factor with groundwater level by wavelet transform, using deep learning algorithms such as recurrent neural networks (RNN) and long short-term memory (LSTM) model to summarize and predict the impact of multiple variable factors on the groundwater level under different time lags. The results of hourly prediction show that the performance of the LSTM model and RNN model are both reliable in which values of the coefficient of determination () were obtained 0.813 and 0.784, respectively.This study provides a feasible and accurate approach for groundwater level prediction by understanding and predicting different water level changes that may occur in the Daliao area in advance. As a result, the study will be an important reference for groundwater resources management and risk assessment, and achieve the goal of sustainable use of groundwater resources.&#160;Keywords Groundwater prediction, Wavelet transform, Risk assessment, LSTM

Download Full-text

Focused small-scale fisheries as complex systems using deep learning models

Latin American Journal of Aquatic Research ◽

10.3856/vol49-issue2-fulltext-2622 ◽

2021 ◽

Vol 49 (2) ◽

pp. 342-353

Author(s):

Ricardo Cavieses-Núñez ◽

Miguel A. Ojeda-Ruiz ◽

Alfredo Flores-Irigollen ◽

Elvia Marín-Monroy ◽

Mirtha Lbañez-Lucero ◽

...

Keyword(s):

Deep Learning ◽

Environmental Variables ◽

Predictive Power ◽

Small Scale ◽

Learning Models ◽

Small Scale Fisheries ◽

Productive Activities ◽

Lack Of Information ◽

Management Measures ◽

The Face

Small-scale fishing (SSF) is a relevant economic activity worldwide, so sustainable development will be essential to assure its contributions to food security, poverty alleviation, and healthy ecosystems. However, the wide diversity of fisheries, their complexity, and the lack of information limit the ability to propose/evaluate management measures and plans and their effects on communities and other productive activities. The state of Baja California Sur, Mexico, our study case, ranks as the third place in national fisheries production, possesses SSF fleets, has a wide variety of fisheries that share fishing areas, fishing seasons, and operating units. In this work, assuming SSF as a complex system were proposed deep learning models (DLM) to forecast the catch volumes, evaluate each input variable's importance, and find interactions. Environmental variables and catch fisheries were tested in the DLM to estimate their predictive power. Different DLM structures and parameters to find the optimal model was used. The variables that presented higher predictive power are the environmental variables with R = 0.90. Moreover, when used in combination with the catches from other areas, the performance of R = 0.95 is obtained. Using only the catches, the model has an R = 0.81. This model allows the use of variables that indirectly affect the system and demonstrates a useful tool to assess a complex system's state in the face of disturbances in its variables.

Download Full-text

Using a boundary-corrected wavelet transform coupled with machine learning and hybrid deep learning approaches for multi-step water level forecasting in Lakes Michigan and Ontario

10.5194/egusphere-egu2020-4233 ◽

2020 ◽

Author(s):

Rahim Barzegar ◽

Jan Adamowski ◽

John Quilty ◽

Mohammad Taghi Aalami

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Wavelet Transform ◽

Great Lakes ◽

Water Level ◽

Root Mean Square ◽

Percentage Error ◽

Mean Square ◽

The Individual ◽

Mother Wavelets

Accurate water level (WL) forecasting is important for water resources management and planning purposes in the Great Lakes. The objectives of this research are two-fold.&#160; The first objective is to apply machine learning (ML) (i.e., random forest (RF) and support vector regression (SVR)) and hybrid convolutional neural network(CNN)-long-short term memory (LSTM) deep learning (DL) models for multi-step (i.e., one-, two- and three-monthly step ahead) WL forecasting in the Great Lakes (Michigan and Ontario). The second objective is to integrate the boundary corrected (BC) maximal overlap discrete wavelet transform (MODWT) with SVR, RF, and CNN-LSTM models to improve the performance of the individual models. By employing a BC-wavelet decomposition method, the &#8216;future data&#8217; issue (i.e., data from the future that is not available), often overlooked in the literature and a major barrier to achieving realistic forecasting performance is overcome.&#160;For Lakes Michigan and Ontario, 1212 monthly WL (m) records (spanning Jan 1918&#8211;Dec 2018) were used to develop the models. For the non-wavelet-based models (SVR, RF, and CNN-LSTM), candidate model inputs included the WL recorded over the previous 12 months.&#160; For the BC-MODWT-based models (BC-MODWT-SVR, BC-MODWT-RF, and BC-MODWT-CNN-LSTM), the lagged input time series were decomposed into BC-wavelet and scaling coefficients by using different mother wavelets (Haar, Daubechies, Symlets, Fejer-Korovkin and Coiflets), filter lengths (from two up to 12) and decomposition levels (from one up to seven).&#160; For each method (SVR, RF, and CNN-LSTM), mother wavelet, and decomposition level a model was generated.&#160; For both wavelet- and non-wavelet-based models, the particle swarm optimization (PSO) method was used to select the most appropriate inputs to include in the proposed multi-step WL forecasting models.The datasets were partitioned into calibration and validation subsets. After calibrating the models, various performance evaluation metrics, e.g., coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), root mean square percentage error (RMSPE), mean absolute percentage error (MAPE) and the Nash-Sutcliffe efficiency coefficient (NSC) were used to assess model accuracy.Of the ML models, the SVR outperformed RF while the DL models outperformed the ML models for each forecast lead time (one-, two-, and three-step(s) ahead). Results from this case study indicate that not all wavelet families and decomposition levels perform equally and in some cases, the wavelet-based models do not improve performance over the non-wavelet-based models. However, the BC-MODWT-CNN-LSTM using suitable mother wavelets (e.g., Haar) outperforms the individual ML and BC-MODWT-ML-based models. More accurate forecasts were obtained for Lake Michigan although the performance in both Great Lakes was accurate. The outcomes of this research indicate that the BC-MODWT-CNN-LSTM model is a promising tool for generating accurate WL forecasts.

Download Full-text

A Conceptual Model for Internet of Things Risk Assessment in Healthcare Domain with Deep Learning Approach

International Journal of Innovative Computing ◽

10.11113/ijic.v10n2.263 ◽

2020 ◽

Vol 10 (2) ◽

Author(s):

Mohd Nizam Zakaria ◽

Nur Azaliah Abu Bakar ◽

Hafiza Abas ◽

Noor Hafizah Hassan

Keyword(s):

Risk Assessment ◽

Deep Learning ◽

Internet Of Things ◽

Risk Mitigation ◽

Assessment Model ◽

It Industry ◽

Risk Assessment Models ◽

Review Analysis ◽

The Internet Of Things

The Internet of Things (IoT) has become a prevalent technology in the IT industry. One of the industries that can benefit extensively in this technology is healthcare. However, the healthcare IoT is still under debate with several studies suggesting it is lack of interoperability, security, and too much complexity. Even more, the risk involved in deploying it is still enormous. Many traditional risk assessment models are unable to provide a specific IoT risk guideline and specification, especially in the healthcare area. Thus, it is essential to understand the full extent of the IoT risk and how to manage its risk in the healthcare area. The risk management models, such as NIST SP 800-30, ISO/IEC 27005, OCTAVE, CRAMM, and EBIOS, which are among the leading and widely used in many areas and healthcare fields, have also been described. Besides, this paper includes a review of three IoT risk assessment models that are based on ABA-IDS, Deep Learning, and AHP-SVM. Based on the review analysis, we proposed a new enhanced healthcare IoT risk assessment model, which aims to provide a real-time monitoring and mitigating risks that incorporate the NIST SP 800-30 framework, ABA-IDS, and CNN deep learning. This shall constitute a better classification of each risk identified to find the best risk mitigation plan.

Download Full-text

Coupling a hybrid CNN-LSTM deep learning model with a Boundary Corrected Maximal Overlap Discrete Wavelet Transform for multiscale Lake water level forecasting

Journal of Hydrology ◽

10.1016/j.jhydrol.2021.126196 ◽

2021 ◽

Vol 598 ◽

pp. 126196

Author(s):

Rahim Barzegar ◽

Mohammad Taghi Aalami ◽

Jan Adamowski

Keyword(s):

Deep Learning ◽

Wavelet Transform ◽

Discrete Wavelet Transform ◽

Water Level ◽

Lake Water ◽

Learning Model ◽

Discrete Wavelet ◽

Lake Water Level ◽

Deep Learning Model

Download Full-text

A deep learning-based quality assessment model of collaboratively edited documents: A case study of Wikipedia

Journal of Information Science ◽

10.1177/0165551519877646 ◽

2019 ◽

pp. 016555151987764

Author(s):

Ping Wang ◽

Xiaodan Li ◽

Renli Wu

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Complete Information ◽

Classification Performance ◽

Machine Learning Algorithms ◽

Assessment Model ◽

Learning Models ◽

Proposed Model

Wikipedia is becoming increasingly critical in helping people obtain information and knowledge. Its leading advantage is that users can not only access information but also modify it. However, this presents a challenging issue: how can we measure the quality of a Wikipedia article? The existing approaches assess Wikipedia quality by statistical models or traditional machine learning algorithms. However, their performance is not satisfactory. Moreover, most existing models fail to extract complete information from articles, which degrades the model’s performance. In this article, we first survey related works and summarise a comprehensive feature framework. Then, state-of-the-art deep learning models are introduced and applied to assess Wikipedia quality. Finally, a comparison among deep learning models and traditional machine learning models is conducted to validate the effectiveness of the proposed model. The models are compared extensively in terms of their training and classification performance. Moreover, the importance of each feature and the importance of different feature sets are analysed separately.

Download Full-text

Evaluation of Groundwater Resources in Aiyar Basin: A GIS Approach for Agricultural Planning and Development

Geosfera Indonesia ◽

10.19184/geosi.v4i3.14954 ◽

2019 ◽

Vol 4 (3) ◽

pp. 302 ◽

Cited By ~ 5

Author(s):

K Balasubramani ◽

M Gomathi ◽

K Kumaraswamy

Keyword(s):

Water Level ◽

Groundwater Level ◽

Hot Spot ◽

Groundwater Resources ◽

Water Level Fluctuations ◽

Cropping Pattern ◽

Hot Spot Analysis ◽

Post Monsoon ◽

Agricultural Planning ◽

Spot Analysis

Groundwater is an integral part of agriculture and rural development. In the present study, an attempt has been made to analyse the spatio-temporal variations of groundwater level in Aiyar basin using spatial statistics and GIS so as to associate the variations with cropping pattern; to suggest agricultural planning and development practices. The groundwater level was measured in the basin through 40 dug wells in the months of July (pre-monsoon) and January (post-monsoon) besides water level data collected from 50 permanent monitoring wells for a period of thirty-six years (1980-2015) from the State Groundwater Division for spatial and statistical analyses. In order to understand the fluctuations in the groundwater level of the basin, seasonal groundwater levels were computed for pre and post-monsoon seasons. To understand the regional variations in water level fluctuations, hot spot analysis is carried out using Getis-Ord Gi* statistics in GIS. Based on z-score, the basin is divided into five clusters. The long-term fluctuation of groundwater level in each cluster was examined independently and the trends were determined. Based on the trend of groundwater level and cropping pattern of the clusters, suggestions are drawn for each cluster for agricultural planning and development. By comparing the clusters, it is found that the foot of Kollimalai and Pachamalai hills (cluster-4 and 5) experiences a severe drop in groundwater level. During the last 36 years, the water table of these clusters is decreased from 4 m to 10 m BGL and the rate of decline is very severe after the drought years of 2002-2003. The main reason for the declining water level in this region is the cultivation of wet crops especially paddy and sugarcane in extensive areas, although irrigation facilities are limited and the climate is conducive only for rainfed agriculture. Hence, it is necessitated to reduce the acreage of wet crops and compensate by suitable dry crops in these clusters. Keywords: Groundwater, Agriculture, GIS, Hot Spot Analysis, River basin, SDG

Download Full-text

Application of Visual MODFLOW to the Dynamic Change and Simulation of Deep Groundwater in Dezhou City, China

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.113-116.1025 ◽

2010 ◽

Vol 113-116 ◽

pp. 1025-1030

Author(s):

Juan Feng ◽

Guan Qun Liu ◽

Quan Sheng Zhao

Keyword(s):

Water Level ◽

Groundwater Level ◽

Groundwater Resources ◽

Dynamic Change ◽

Underground Water ◽

Current Situation ◽

Visual Modflow ◽

Deep Groundwater ◽

Pumping Rate ◽

Groundwater Exploitation

In view of this major environmental geology problem in Dezhou City that continuous overexploiting of deep groundwater has caused he rapidly-expansion of groundwater drop funnel in recent years, the dynamic change of deep groundwater in Dezhou City was systematically analyzed as well as the evolution and development of hydrodynamic field and deep drawdown cone in temporal and spatial variation was simulated by the application of the numerical Model. On the basis of hydrogeological conditions generalized in this region, Visual MODFLOW software was applied to build mathematical model of groundwater and stimulate the seepage field of groundwater. It predicted the expansion of groundwater drop funnel and the change of underground water level under the conditions of exploitation situation and different designed exploiting volume by the model built. The depth reduction and variation of groundwater under different design schemes for pumping rate were argued by contrast analysis of the calculated results. The forecasting result under the current situation of groundwater exploitation indicates that the drawdown of water level would increase more with the continuous exploitation when the exploiting volume of current situation is 2047×104m3/a. When (time)is equal to 5a(2013), (the decline depth of groundwater) is at 4.81～22.65m and the annual deceleration is at 0.96～4.53m/a. When is equal to 10a(2018), is at 14.32～32.87m as well as the annual deceleration is at 1.43～3.29m/a, and then the average elevation of central water level of funnel is -118.06m. The forecasting results under different design schemes for exploiting volume showed that the groundwater level would continuously decrease if the present exploiting quantity is still kept at 2047×104m3/a, which the depth of central groundwater level of funnel is 144.95m in 2012. While exploiting quantity cuts down to 1950×104m3/a, the groundwater level still constantly decreases, which the depth of central groundwater level of funnel is 133.90m in 2012. Only when exploiting quantity further cut down to 1750×104m3/a, the groundwater level would never descend after 2011, and then it would begin ascending, which the depth of central groundwater level of funnel would be 120.25m in 2012. According to the model stimulation of groundwater flow and the results of water balance analysis, the exploitation project was proposed that the drawdown cone would not further expand. The key measure to protect deep groundwater resources in this region is scientific planning of underground water, and ensuring that The allowable exploiting volume in this region should be kept at 1750×104m3/a in order that it can reach a benign circle with the balance of exploitation and supplementation.

Download Full-text

A Deep Learning–Based Decision Support Tool for Precision Risk Assessment of Breast Cancer

JCO Clinical Cancer Informatics ◽

10.1200/cci.18.00121 ◽

2019 ◽

pp. 1-12 ◽

Cited By ~ 4

Author(s):

Tiancheng He ◽

Mamta Puppala ◽

Chika F. Ezeana ◽

Yan-siang Huang ◽

Ping-hsuan Chou ◽

...

Keyword(s):

Breast Cancer ◽

Risk Assessment ◽

Deep Learning ◽

Breast Cancer Risk ◽

Cancer Risk ◽

Breast Imaging ◽

Assessment Model ◽

Specific Patient ◽

Mammographic Images ◽

Abnormal Mammogram

PURPOSE The Breast Imaging Reporting and Data System (BI-RADS) lexicon was developed to standardize mammographic reporting to assess cancer risk and facilitate the decision to biopsy. Because of substantial interobserver variability in the application of the BI-RADS lexicon, the decision to biopsy varies greatly and results in overdiagnosis and excessive biopsies. The false-positive rate from mammograms is estimated to be 7% to approximately 10% overall, but within the BI-RADS 4 category, it is greater than 70%. Therefore, we developed the Breast Cancer Risk Calculator (BRISK) to target a well-characterized and specific patient subgroup (BI-RADS 4) rather than a broad heterogeneous group in assessing breast cancer risk. METHODS BRISK provides a novel precise risk assessment model to reduce overdiagnosis and unnecessary biopsies. It was developed by applying natural language processing and deep learning methods on 5,147 patient records archived in the Houston Methodist systemwide data warehouse from 2006 to May 2015, including imaging and pathology reports, mammographic images, and patient demographics. Key characteristics for BI-RADS 4 patients were collected and computed to output an index measure for biopsy recommendation that is clinically relevant and informative and improves upon the traditional BI-RADS 4 scores. RESULTS For the validation set, we assessed data from 1,247 BI-RADS 4 patients, including mammographic images and medical reports. The BRISK model sensitivity to predict malignancy was 100%, whereas the specificity was 74%. The total accuracy of our implemented model in BRISK was 81%. Overall area under the curve was 0.93. CONCLUSION BRISK for abnormal mammogram uses integrative artificial intelligence technology and has demonstrated high sensitivity in the prediction of malignancy. Prospective evaluation is under way and can lead to improvement in patient-physician engagement in making informed decisions with regard to biopsy.

Download Full-text

Deep learning models for the prediction of small-scale fisheries catches: finfish fishery in the region of “Bahía Magadalena-Almejas”

ICES Journal of Marine Science ◽

10.1093/icesjms/fsy065 ◽

2018 ◽

Vol 75 (6) ◽

pp. 2088-2096 ◽

Cited By ~ 1

Author(s):

Ricardo Alberto Cavieses Núñez ◽

Miguel Ángel Ojeda Ruiz de la Peña ◽

Alfredo Flores Irigollen ◽

Manuel Rodríguez Rodríguez

Keyword(s):

Deep Learning ◽

Short Term Memory ◽

Low Cost ◽

Small Scale ◽

Learning Models ◽

Small Scale Fisheries ◽

Relevant Role ◽

Important Challenge ◽

Memory Network ◽

Using Data

Abstract Globally, over 80% of fisheries are at maximum sustainable levels or overexploited. However, small-scale fisheries (SSFs) in developing countries play a relevant role in coastal communities’ development with important impacts on the economy. The SSFs are normally multi-specific and due to the lack of data, studying them by simulation poses an important challenge especially forecasting models. These models are necessary to support management decisions or develop sustainable fisheries; therefore, models based on Deep Learning were proposed to forecast SSFs catch, using data from official catch landing reports (OCLRs), satellite images, and oceanographic data. The finfish fishery in Bahía Magdalena-Almejas (México) was used for the present study. According to an analysis of OCLRs, the target species of major importance in the fishery were identified and selected for the model. The proposed deep learning models used two artificial neural networks structures: non-linear autoregressive neural network and long-short term memory network, which were designed to assess and forecast monthly catch levels of Paralabrax nebulifer and Caulolatilus princeps. Models with a performance efficiency of R > 0.8, MSE < 300 were found, which indicate that the models are applicable in SSF with poor data and multi-specific fishery contexts, at low cost.

Download Full-text