1
|
Tran TTK, Janizadeh S, Bateni SM, Jun C, Kim D, Trauernicht C, Rezaie F, Giambelluca TW, Panahi M. Improving the prediction of wildfire susceptibility on Hawai'i Island, Hawai'i, using explainable hybrid machine learning models. J Environ Manage 2024; 351:119724. [PMID: 38061099 DOI: 10.1016/j.jenvman.2023.119724] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/28/2023] [Revised: 11/13/2023] [Accepted: 11/25/2023] [Indexed: 01/14/2024]
Abstract
This study presents a comparative analysis of four Machine Learning (ML) models used to map wildfire susceptibility on Hawai'i Island, Hawai'i. Extreme Gradient Boosting (XGBoost) combined with three meta-heuristic algorithms - Whale Optimization (WOA), Black Widow Optimization (BWO), and Butterfly Optimization (BOA) - were employed to map areas susceptible to wildfire. To generate a wildfire inventory, 1408 wildfire points were identified within the study area from 2004 to 2022. The four ML models (XGBoost, WOA-XGBoost, BWO-XGBoost, and BOA-XGBoost) were run using 14 wildfire-conditioning factors categorized into four main groups: topographical, meteorological, vegetation, and anthropogenic. Six performance metrics - sensitivity, specificity, positive predictive values, negative predictive values, the Area Under the receiver operating characteristic Curve (AUC), and the average precision (AP) of Precision-Recall Curves (PRCs) - were used to compare the predictive performance of the ML models. The SHapley Additive exPlanations (SHAP) framework was also used to interpret the importance values of the 14 influential variables for the modeling of wildfire on Hawai'i Island using the four models. The results of the wildfire modeling indicated that all four models performed well, with the BWO-XGBoost model exhibiting a slightly higher prediction performance (AUC = 0.9269), followed by WOA-XGBoost (AUC = 0.9253), BOA-XGBoost (AUC = 0.9232), and XGBoost (AUC = 0.9164). SHAP analysis revealed that the distance from a road, annual temperature, and elevation were the most influential factors. The wildfire susceptibility maps generated in this study can be used by local authorities for wildfire management and fire suppression activity.
Collapse
Affiliation(s)
- Trang Thi Kieu Tran
- Department of Civil, Environmental and Construction Engineering and Water Resources Research Center, University of Hawai'i at Manoa, Honolulu, HI, 96822, USA.
| | - Saeid Janizadeh
- Department of Civil, Environmental and Construction Engineering and Water Resources Research Center, University of Hawai'i at Manoa, Honolulu, HI, 96822, USA.
| | - Sayed M Bateni
- Department of Civil, Environmental and Construction Engineering and Water Resources Research Center, University of Hawai'i at Manoa, Honolulu, HI, 96822, USA.
| | - Changhyun Jun
- Department of Civil and Environmental Engineering, College of Engineering, Chung-Ang University, Seoul, 06974, Republic of Korea.
| | - Dongkyun Kim
- Department of Civil Engineering, Hongik University, Mapo-Gu, Seoul, Republic of Korea.
| | - Clay Trauernicht
- Department of Natural Resources and Environmental Management, University of Hawai'i at Manoa, Honolulu, HI, 96822, USA.
| | - Fatemeh Rezaie
- Department of Civil, Environmental and Construction Engineering and Water Resources Research Center, University of Hawai'i at Manoa, Honolulu, HI, 96822, USA; Geoscience Data Center, Korea Institute of Geoscience and Mineral Resources (KIGAM), 124 Gwahak-ro, Yuseong-gu, Daejeon, 34132, Republic of Korea; Department of Geophysical Exploration, Korea University of Science and Technology, 217 Gajeong-ro, Yuseong-gu, Daejeon, 34113, Republic of Korea.
| | - Thomas W Giambelluca
- Water Resources Research Center, University of Hawai'i at Manoa, Honolulu, HI, 96822, USA.
| | - Mahdi Panahi
- Department of Civil, Environmental and Construction Engineering and Water Resources Research Center, University of Hawai'i at Manoa, Honolulu, HI, 96822, USA.
| |
Collapse
|
2
|
Jaafari A, Janizadeh S, Abdo HG, Mafi-Gholami D, Adeli B. Understanding land degradation induced by gully erosion from the perspective of different geoenvironmental factors. J Environ Manage 2022; 315:115181. [PMID: 35500480 DOI: 10.1016/j.jenvman.2022.115181] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/05/2021] [Revised: 04/10/2022] [Accepted: 04/24/2022] [Indexed: 06/14/2023]
Abstract
Complex interrelationships between landscape-level geoenvironmental factors and natural phenomena have rendered land degradation control measures ineffective. For control to be effective, this study argues that the interactions between different geoenvironmental factors and gully erosion (as an indicator of land degradation) should be more fully investigated and spatially mapped. To do so, gully locations of the Konduran watershed, Iran, were detected in the field and modeled in response to seventeen geoenvironmental factors using three machine learning methods, i.e., multivariate adaptive regression splines (MARS), random forest (RF), regularized random forest (RRF), and Bayesian generalized linear model (Bayesian GLM). The models' performance was validated, the relationship of gully occurrence with each factor was quantified, the probability of gully erosion (i.e., land degradation) was retrospectively estimated, and the spatially explicit maps of land degradation susceptibility were produced. Based on the area under the receiver operating characteristic curve (AUC), the RRF and MARS models with AUC = 0.98 achieved the greatest goodness-of-fit with the training dataset, whereas the RF model with AUC = 0.83 showed the greatest ability in predicting future gully occurrences. Further scrutinization using the sensitivity and specificity metrics demonstrated the efficiency of the RF model for correctly classifying the gully (sensitivity-training = 92%; sensitivity-validation = 90%) and non-gully (specificity-training = 95%; specificity-validation = 68%) pixels. Nearly 13% of the study area ended up being the hardest hit region due to their general characteristics of distance from roads and rives, altitude, and normalized difference vegetation index (NDVI) that were identified as the most influential factors in gully erosion occurrence. Given the resolution quality and reliable predictive accuracy, our spatially explicit maps of land susceptibility to gully erosion can be used by authorities and urban planners for identifying the target areas for rehabilitation and making more informed decisions for infrastructure development. Although our study was strictly focused on a certain region, our recommendations and implications are of global significance.
Collapse
Affiliation(s)
- Abolfazl Jaafari
- Research Institute of Forests and Rangelands, Agricultural Research, Education and Extension Organization (AREEO), Tehran, 1496813111, Iran.
| | - Saeid Janizadeh
- Department of Watershed Management Engineering and Sciences, Faculty in Natural Resources and Marine Science, Tarbiat Modares University, Tehran, 14115-111, Iran
| | - Hazem Ghassan Abdo
- Geography Department, Faculty of Arts and Humanities, Tartous University, Tartous, Syria; Geography Department, Faculty of Arts and Humanities, Damascus University, Damascus, Syria; Geography Department, Faculty of Arts and Humanities, Tishreen University, Lattakia, Syria
| | - Davood Mafi-Gholami
- Department of Forest Sciences, Faculty of Natural Resources and Earth Sciences, Shahrekord University, Shahrekord, 8818634141, Iran
| | | |
Collapse
|
3
|
Alkindi KM, Mukherjee K, Pandey M, Arora A, Janizadeh S, Pham QB, Anh DT, Ahmadi K. Prediction of groundwater nitrate concentration in a semiarid region using hybrid Bayesian artificial intelligence approaches. Environ Sci Pollut Res Int 2022; 29:20421-20436. [PMID: 34735705 DOI: 10.1007/s11356-021-17224-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/22/2021] [Accepted: 10/21/2021] [Indexed: 06/13/2023]
Abstract
Nitrate is a major pollutant in groundwater whose main source is municipal wastewater and agricultural activities. In the present study, Bayesian approaches such as Bayesian generalized linear model (BGLM), Bayesian regularized neural network (BRNN), Bayesian additive regression tree (BART), and Bayesian ridge regression (BRR) were used to model groundwater nitrate contamination in a semiarid region Marvdasht watershed, Fars province, Iran. Eleven groundwater (GW) nitrate conditioning factors have been taken as input parameters for predictive modeling. The results showed that the Bayesian models used in this study were all competent to model groundwater nitrate and the BART model with R2 = 0.83 was more efficient than the other models. The result of variable importance showed that potassium (K) has the highest importance in the models followed by rainfall, altitude, groundwater depth, and distance from the residential area. The results of the study can support the decision-making process to control and reduce the sources of nitrate pollution.
Collapse
Affiliation(s)
- Khalifa M Alkindi
- UNESCO Chair on Aflaj Studies, Archaeohydrology, University of Nizwa, Nizwa, Oman
| | - Kaustuv Mukherjee
- Department of Geography, Chandidas Mahavidyalaya, Birbhum, WB, 731215, India
| | - Manish Pandey
- University Center for Research & Development (UCRD), Chandigarh University, Mohali, 140413, Punjab, India
- Department of Civil Engineering, University Institute of Engineering, Chandigarh University, Mohali, 140413, Punjab, India
| | - Aman Arora
- Department of Geography, Faculty of Natural Sciences, Jamia Millia Islamia, New Delhi, 10025, Delhi, India
| | - Saeid Janizadeh
- Department of Watershed Management Engineering and Sciences, Faculty in Natural Resources and Marine Science, Tarbiat Modares University, 14115-111, Tehran, Iran
| | - Quoc Bao Pham
- Institute of Applied Technology, Thu Dau Mot University, Binh Duong Province, Vietnam
| | - Duong Tran Anh
- Ho Chi Minh City University of Technology (HUTECH) 475A, Dien Bien Phu, Ward 25, Binh Thanh District, Ho Chi Minh City, Vietnam.
| | - Kourosh Ahmadi
- Department of Forestry, Faculty in Natural Resources and Marine Science, Tarbiat Modares University, 14115-111, Tehran, Iran
| |
Collapse
|
4
|
Janizadeh S, Chandra Pal S, Saha A, Chowdhuri I, Ahmadi K, Mirzaei S, Mosavi AH, Tiefenbacher JP. Mapping the spatial and temporal variability of flood hazard affected by climate and land-use changes in the future. J Environ Manage 2021; 298:113551. [PMID: 34435571 DOI: 10.1016/j.jenvman.2021.113551] [Citation(s) in RCA: 24] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/13/2021] [Revised: 07/13/2021] [Accepted: 08/13/2021] [Indexed: 06/13/2023]
Abstract
The predicts current and future flood risk in the Kalvan watershed of northwestern Markazi Province, Iran. To do this, 512 flood and non-flood locations were identified and mapped. Twenty flood-risk factors were selected to model flood risk using several machine learning techniques: conditional inference random forest (CIRF), the gradient boosting model (GBM), extreme gradient boosting (XGB) and their ensembles. To investigate the future (year 2050) effects of changing climates and changing land use on future flood risk, a general circulation model (GCM) with representative concentration pathways (RCPs) of the 2.6 and 8.5 scenarios by 2050 was tested for impacts on 8 precipitation variables. In addition, future land uses in 2050 was prepared using a CA-Markov model. The performances of the flood risk models were validated with Receiver Operating Characteristic-Area Under Curve (ROC-AUC) and other statistical analyses. The AUC value of the ROC curve indicates that the ensemble model had the highest predictive power (AUC = 0.83) and was followed by GBM (AUC = 0.80), XGB (AUC = 0.79), and CIRF (AUC = 0.78). The results of climate and land use changes on future flood-prone areas showed that the areas classified as having moderate to very high flood risk will increase by 2050. Due to the changes occurring with land uses and in climates, the area classified as moderate to very high risk increased in the predictions from all four models. The areal proportion classes of the risk zones in 2050 under the RCP 2.6 scenario using the ensemble model have changed of the following proportions from the current distribution Very Low = -12.04 %, Low = -8.56 %, Moderate = +1.56 %, High = +11.55 %, and Very High = +7.49 %. The RCP 8.5 scenario has caused the following changes from the present percentages: Very Low = -14.48 %, Low = -6.35 %, Moderate = +4.54 %, High = +10.61 %, and Very High = +5.67 %. The results of current and future flood risk mapping can aid planners and flood hazard managers in their efforts to mitigate impacts.
Collapse
Affiliation(s)
- Saeid Janizadeh
- Department of Watershed Management Engineering and Sciences, Faculty in Natural Resources and Marine Science, Tarbiat Modares University, Tehran, 14115-111, Iran.
| | | | - Asish Saha
- Department of Geography, The University of Burdwan, West Bengal, India.
| | | | - Kourosh Ahmadi
- Department of Forestry, Faculty in Natural Resources and Marine Science, Tarbiat Modares University, Tehran, 14115-111, Iran.
| | - Sajjad Mirzaei
- Department of Watershed Management Engineering and Sciences, Faculty in Natural Resources and Marine Science, Tarbiat Modares University, Tehran, 14115-111, Iran.
| | - Amir Hossein Mosavi
- John von Neumann Faculty of Informatics, Obuda University, 1034, Budapest, Hungary; Department of Informatics, J. Selye University, 94501, Komarno, Slovakia.
| | - John P Tiefenbacher
- Department of Geography, Texas State University, San Marcos, TX, 78666, United States.
| |
Collapse
|
5
|
Cerdà A, Novara A, Dlapa P, López-Vicente M, Úbeda X, Popović Z, Mekonnen M, Terol E, Janizadeh S, Mbarki S, Saldanha-Vogelmann E, Hazrati S, Sannigrahi S, Parhizkar M, Giménez-Morera A. Rainfall and water yield in Macizo del Caroig, Eastern Iberian Peninsula. Event runoff at plot scale during a rare flash flood at the Barranco de Benacancil. ACTA ACUST UNITED AC 2021. [DOI: 10.18172/cig.4833] [Citation(s) in RCA: 21] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
Abstract
Floods are a consequence of extreme rainfall events. Although surface runoff generation is the origin of discharge, flood research usually focuses on lowlands where the impact is higher. Runoff and sediment delivery at slope and pedon scale receiving much less attention in the effort to understand flood behaviour in time and space. This is especially relevant in areas where, due to climatic and hydrogeological conditions, streams are ephemeral, so-called dry rivers (“wadis”, "ramblas" or “barrancos”) that are widespread throughout the Mediterranean. This paper researches the relationship between water delivery at pedon and slope scale with dry river floods in Macizo del Caroig, Eastern Iberian Peninsula. Plots of 1x1, 1x2, 1x4, and 2x8 m located in the “El Teularet” Soil Erosion and Degradation Research Station were monitored from 2004 to 2014 to measure soil and water delivery. Rainfall and flow at the dry river Barranco de Benacancil were also monitored. Results show that runoff and sediment discharge were concentrated in few events during the 11 years of research. A single flood event was registered in the channel on September 28, 2009, however, the runoff was registered 160 times at the plots. Runoff discharge was dependent on the size of the plots, with larger plots yielding lower runoff discharge per unit area, suggesting short runoff-travel distance and duration. Three rainfall events contributed with 26% of the whole runoff discharge, and five achieved 56% of the runoff. We conclude that the runoff generated at the plot scale is disconnected from the main channel. From a spatial point of view, there is a decrease in runoff coefficient along the slope. From a temporal point of view, the runoff is concentrated in a few rainfall events. These results show that the runoff generated at plot and slope scale does not contribute to the floods except for rainfall events with more than 100 mm day-1. The disconnection of the runoff and sediment delivery is confirmed by the reduction in the runoff delivery at plot scale due to the control of the length of the plot (slope) on the runoff and sediment delivery.
Collapse
|
6
|
Chen W, Lei X, Chakrabortty R, Chandra Pal S, Sahana M, Janizadeh S. Evaluation of different boosting ensemble machine learning models and novel deep learning and boosting framework for head-cut gully erosion susceptibility. J Environ Manage 2021; 284:112015. [PMID: 33515838 DOI: 10.1016/j.jenvman.2021.112015] [Citation(s) in RCA: 18] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/16/2020] [Revised: 12/20/2020] [Accepted: 01/16/2021] [Indexed: 06/12/2023]
Abstract
The objective of this study is to assess the gully head-cut erosion susceptibility and identify gully erosion prone areas in the Meimand watershed, Iran. In recent years, this study area has been greatly influenced by several head-cut gullies due to unusual climatic factors and human induced activity. The present study is therefore intended to address this issue by developing head-cut gully erosion prediction maps using boosting ensemble machine learning algorithms, namely Boosted Tree (BT), Boosted Generalized Linear Models (BGLM), Boosted Regression Tree (BRT), Extreme Gradient Boosting (XGB), and Deep Boost (DB). Initially, we produced a gully erosion inventory map using a variety of resources, including published reports, Google Earth images, and field records of the Global Positioning System (GPS). Subsequently, we distributed this information randomly and choose 70% (102) of the test gullies and the remaining 30% (43) for validation. The methodology was designed using morphometric and thematic determinants, including 14 head-cut gully erosion conditioning features. We have also investigated the following: (a) Multi-collinearity analysis to determine the linearity of the independent variables, (b) Predictive capability of piping models using train and test dataset and (c) Variables importance affecting head-cut gully erosion. The study reveals that altitude, land use, distances from road and soil characteristics influenced the method with the greatest impact on head-cut gully erosion susceptibility. We presented five head-cut gully erosion susceptibility maps and investigated their predictive accuracy through area under curve (AUC). The AUC test reveals that the DB machine learning method demonstrated significantly higher accuracy (AUC = 0.95) than the BT (AUC = 0.93), BGLM (AUC = 0.91), BRT (AUC = 0.94) and XGB (AUC = 0.92) approaches. The predicted head-cut gully erosion susceptibility maps can be used by policy makers and local authorities for soil conservation and to prevent threats to human activities.
Collapse
Affiliation(s)
- Wei Chen
- College of Geology & Environment, Xi'an University of Science and Technology, Xi'an, 710054, Shaanxi, China; Key Laboratory of Coal Resources Exploration and Comprehensive Utilization, Ministry of Natural Resources, Xi'an, 710021, China.
| | - Xinxiang Lei
- College of Geology & Environment, Xi'an University of Science and Technology, Xi'an, 710054, Shaanxi, China.
| | | | | | - Mehebub Sahana
- Research Associate, School of Environment, Education & Development, University of Manchester, UK.
| | - Saeid Janizadeh
- Department of Watershed Management Engineering and Sciences, Faculty in Natural Resources and Marine Science, Tarbiat Modares University, Tehran, 14115-111, Iran.
| |
Collapse
|
7
|
Band SS, Janizadeh S, Chandra Pal S, Saha A, Chakrabortty R, Shokri M, Mosavi A. Novel Ensemble Approach of Deep Learning Neural Network (DLNN) Model and Particle Swarm Optimization (PSO) Algorithm for Prediction of Gully Erosion Susceptibility. Sensors (Basel) 2020; 20:E5609. [PMID: 33008132 PMCID: PMC7582716 DOI: 10.3390/s20195609] [Citation(s) in RCA: 70] [Impact Index Per Article: 17.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/11/2020] [Revised: 09/22/2020] [Accepted: 09/24/2020] [Indexed: 11/16/2022]
Abstract
This study aims to evaluate a new approach in modeling gully erosion susceptibility (GES) based on a deep learning neural network (DLNN) model and an ensemble particle swarm optimization (PSO) algorithm with DLNN (PSO-DLNN), comparing these approaches with common artificial neural network (ANN) and support vector machine (SVM) models in Shirahan watershed, Iran. For this purpose, 13 independent variables affecting GES in the study area, namely, altitude, slope, aspect, plan curvature, profile curvature, drainage density, distance from a river, land use, soil, lithology, rainfall, stream power index (SPI), and topographic wetness index (TWI), were prepared. A total of 132 gully erosion locations were identified during field visits. To implement the proposed model, the dataset was divided into the two categories of training (70%) and testing (30%). The results indicate that the area under the curve (AUC) value from receiver operating characteristic (ROC) considering the testing datasets of PSO-DLNN is 0.89, which indicates superb accuracy. The rest of the models are associated with optimal accuracy and have similar results to the PSO-DLNN model; the AUC values from ROC of DLNN, SVM, and ANN for the testing datasets are 0.87, 0.85, and 0.84, respectively. The efficiency of the proposed model in terms of prediction of GES was increased. Therefore, it can be concluded that the DLNN model and its ensemble with the PSO algorithm can be used as a novel and practical method to predict gully erosion susceptibility, which can help planners and managers to manage and reduce the risk of this phenomenon.
Collapse
Affiliation(s)
- Shahab S. Band
- Institute of Research and Development, Duy Tan University, Da Nang 550000, Vietnam
- Future Technology Research Center, National Yunlin University of Science and Technology, 123 University Road, Section 3, Douliou, Yunlin 64002, Taiwan
| | - Saeid Janizadeh
- Department of Watershed Management Engineering and Sciences, Faculty in Natural Resources and Marine Science, Tarbiat Modares University, 14115-111 Tehran, Iran;
| | - Subodh Chandra Pal
- Department of Geography, The University of Burdwan, West Bengal, Burdwan 713104, India; (S.C.P.); (A.S.); (R.C.)
| | - Asish Saha
- Department of Geography, The University of Burdwan, West Bengal, Burdwan 713104, India; (S.C.P.); (A.S.); (R.C.)
| | - Rabin Chakrabortty
- Department of Geography, The University of Burdwan, West Bengal, Burdwan 713104, India; (S.C.P.); (A.S.); (R.C.)
| | - Manouchehr Shokri
- Institute of Structural Mechanics, Bauhaus Universität Weimar, 99423 Weimar, Germany;
| | - Amirhosein Mosavi
- Environmental Quality, Atmospheric Science and Climate Change Research Group, Ton Duc ThangUniversity, Ho Chi Minh City 700000, Vietnam;
- Faculty of Environment and Labour Safety, Ton Duc Thang University, Ho Chi Minh City 700000, Vietnam
| |
Collapse
|