Evaluation of the efficiency of three data mining models in zoning areas prone to gully erosion (Case study: Upper Watershed of Boustan Dam)

Document Type : Research/Original/Regular Article

Authors

1 Former Ph.D. Student, Department of Desert Zone Management, Faculty of rangeland and Watershed Management, Gorgan University of Agricultural Sciences and Natural Sciences, Golestan, Iran

2 Associate Professor, Department of Desert Zone Management Faculty of Rangeland and Watershed Management, Gorgan University of Agricultural Sciences and Natural Sciences, Golestan, Iran

3 Assistant Professor, Department of Desert Zone Management, Faculty of Rangeland and Watershed Management, Gorgan University of Agricultural Sciences and Natural Resources, Golestan, Iran

4 Professor, Department of Watershed Management, Faculty of Rangeland and Watershed Management, Gorgan University of Agricultural Sciences and Natural Sciences, Golestan, Iran

5 Professor, Department of Soil Sciences, Faculty of Agriculture, Shiraz University, Shiraz, Iran

Abstract

Introduction
Gully erosion is a particularly destructive form of water erosion that can lead to alarming rates of soil loss, especially in the vulnerable landscapes of dry and semi-arid regions. This type of erosion is recognized not only for its immediate impact on land but also as a critical environmental challenge that requires our urgent attention. As a result, there has been a growing emphasis on developing effective predictive models that can elucidate the temporal and spatial dynamics of gully erosion-specifically, how it forms, expands, and evolves over time. This endeavor has captured the interest of soil conservation experts and researchers alike, who understand the profound implications of this issueIn recent years, remote sensing and data mining techniques have emerged as valuable tools for identifying and mapping areas susceptible to gully erosion. These innovative methods provide essential insights for land managers and policymakers, enabling them to make informed decisions. Furthermore, the effectiveness of predictive models hinges on their advanced capabilities, which enhance their learning potential and improve the identification of relationships among various factors. Creating a sensitivity map is an essential strategy for land use planning, as it actively contributes to reducing land degradation and safeguarding our natural resources. Understanding the connection between gully occurrences and influential factors is not only beneficial; it is crucial for sustainable land management and environmental preservation.
 
Materials and Methods
This research investigates the sensitivity of the upper basin of the Boustan Dam to gully erosion using object-based techniques and data mining algorithms. To achieve this, field visits were conducted to select 81 gullies for analysis. The study examines several factors, including slope, aspect, slope length index (LS), elevation, plan curvature, distance from the river, drainage density, topographic wetness index (TWI), height above the nearest drainage (HAND), average annual rainfall, distance from roads, distance from faults, land use, geomorphology, soil texture, and satellite bands B7, B5, and B3. Additionally, the normalized difference vegetation index (NDVI), normalized difference built-up index (NDBI), and normalized difference water index (NDWI) are considered, along with geological aspects. QuickBird satellite images from 2021 and Orfeo software were utilized to monitor and identify gullies in the area through image segmentation. Initially, a collinearity analysis of 23 effective erosion occurrence indices was performed, resulting in the removal of distance from the fault, digital elevation model (DEM), NDWI, NDBI, and satellite bands B3, B5, and B7 due to their collinearity exceeding five. Following this linear operation, all remaining indices were integrated with the segmentation map obtained from the Orfeo environment. Finally, three models -Random Forest, Maximum Entropy, and Support Vector Machine- were employed to model the selected indices using Python (Colab).
 
Results and Discussion
The results from the object-oriented method in the Orfeo software further demonstrated its effectiveness in accurately identifying gullies. With an impressive accuracy rate of 91.3%, this method has proven to be highly reliable in generating machine learning maps with high precision. Findings indicate that the key factors contributing to gully erosion include the rainfall index, distance from the river, Height Above Nearest Drainage (HAND) index, distance from the road, and valley index. Torrential rain emerged as a significant driver of gully erosion, while the distance from the river was crucial due to the concentration of surface and subsurface flows toward waterways. The HAND index played a prominent role in modeling the sensitivity of the study area compared to other sub-indices derived from DEM, as it exhibited promising applications in assessing natural hazards. Locations close to roads were found to be more vulnerable to water erosion, and valleys were identified as especially susceptible to gully erosion due to their conducive conditions for rapid water flow and erosion. Extensive field studies support this observation. Furthermore, zoning results generated using these indices indicated that, within the random forest model, 544.23 hectares of the area are at high or very high risk of erosion. This model outperformed the Maximum Entropy and Support Vector Machine models in predicting erosion-prone areas. Finally, the ROC curve was utilized to validate the model, yielding AUC values of 0.95 and 0.94 in the random forest model during the training and validation stages, respectively. These results indicate the model's high accuracy in predicting areas highly susceptible to gully erosion.
 
Conclusion
This study effectively used object-based image analysis algorithms and data mining techniques to create a sensitivity map of the region. The object-based method efficiently identified the local gullies using the mean shift algorithm, while the random forest algorithm excelled in predicting areas prone to gully erosion. Key factors contributing to gully erosion were identified, including rainfall, distance from the river, soil HAND index, and distance from roads and valleys. The findings from this study provide valuable insights for managing and preserving basin resources. Implementing the recommendations from this research could help mitigate the impacts of gully erosion in the future and ensure the sustainability of the Boustan Dam and its surrounding ecosystem.

Keywords

Main Subjects


Amatya, P., Kirschbaum, D., Stanley, T., & Tanyas, H. (2021). Landslide mapping using object-based image analysis and open source tools. Engineering Geology, 282, 106000. doi:10.1016/j.enggeo.2021.106000
Arabameri, A., Pradhan, B., & Rezaei, K. (2019). Gully erosion zonation mapping using integrated geographically weighted regression with certainty factor and random forest models in GIS. Environmental Management, 232, 928- 942. doi:10.1016/j.jenvman.2018.11.110.
Arabameri, A., Pradhan, B., Pourghasemi, H., Rezaei, K., & Kerle, N. (2018a). Spatial modeling of gully erosion using GIS and R programing: a comparison among three data mining algorithms. Applied Sciences. 8(8), 1369. doi:10.3390/app8081369
Arabameri, A., Rezaei, KH., & Yamani, M. )2018b(. Analysis of geo-environmental parameters and gully erosion susceptibility mapping in Toroud Watershed using data-driven EBF method. Range and Watershed Management, 71(1), 97-114. doi:10.22071/gsj.2018.114756.1374. [In Persian]
Arabameri, A., Rezaei, Kh., Yamani, M., & Shirani, K. (2018c). Optimization of the sensitivity map to gully erosion using data-driven statistical integrated methods (Case study: Toroud-Najjarabad Basin). Earth Science Research, 10(37), 18-38. doi:10.52547/esrj.10.1.18. [In Persian]
Avand, M., Janizadeh, S., Naghibi, S.A., Pourghasemi, H.R., Khosrobeigi Bozchaloei, S., & Blaschke, T. (2019). A comparative assessment of random forest and k-nearest neighbor classifiers for gully erosion susceptibility mapping. Water, 11(10), 2076. doi:10.3390/w11102076
Azareh, A., Rahmati, O., Rafiei-Sardooi, E., Sankey, J.B., Lee, S., Shahabi, H., & Ahmad, B. (2019). Modeling gully-erosion susceptibility in a semi-arid region, Iran: Investigation of applicability of certainty factor and maximum entropy models. Science of The Total Environment, 655,684–696. doi:10.1016/j.scitotenv.2018.11.235
Bennett, S.J., & Wells, R.R. (2019). Gully erosion processes, disciplinary fragmentation, and technological innovation. Earth surface Processes and Landforms, 44(1), 46-53. doi:10.1002/esp.4522.
Blaschke T., Feizizadeh B., Holbling D. (2014). Object- Based image analysis and digital terrain analysis for locating landslides in the Urmia Lake Basin, Iran. Selected Topics In Applied Earth Observations and Remote Sensing, 7(12), 4806-4817. doi:10.1109/JSTARS.2014.2350036
Blaschke, T. (2003). Object-based contextual image classification built on image segmentation. In Advances in Techniques for Analysis of Remotely Sensed Data, 2003 IEEE Workshop. 113-119. doi:10.1109/WARSD.2003.1295182.
Breiman, L. (2000). Some infinity theory for predictor ensembles. Technical Report 579, Statistics Depatment UCB.
Breiman, L. (2001). Random forests. Machine Learning, 45, 5–32.
Chen, G., Weng, Q., Hay, G.J., & He, Y. (2018a). Geographic object-based image analysis (GEOBIA): emerging trends and future opportunities. GIScience & Remote Sensing, 55(2), 159-182. doi:10.1080/15481603.2018.1426092
Chen, Y., Ming, D., Zhao, L., Lv, B., Zhou, K., & Qing, Y. (2018b). Review on high spatial resolution remote sensing image segmentation evaluation. Photogrammetric Engineering & Remote Sensing, 84(10), 629-646.‏ doi:10.14358/PERS.84.10.629
Conforti, M., Aucelli, P.P., Robustelli, G., & Scarciglia, F. (2011). Geomorphology and GIS analysis for mapping gully erosion susceptibility in the Turbolo stream catchment (Northern Calabria, Italy). Natural Hazards, 56(3), 881-898. doi:10.1007/s11069-010-9598-2
Conoscenti, C., Angileri, S., Cappadonia, C., Rotigliano, E., Agnesi, V., & Märker, M. (2014). Gully erosion susceptibility assessment by means of GIS-based logistic regression: A case of Sicily (Italy). Geomorphology, 204(1), 399–411. doi:10.1016/j.geomorph.2013.08.021
FAO & ITPS. (2015). Status of the World’s Soil Resources (Main Report). FAO, Pp. 608.
Feurer, M., & Hutter, F. (2019). Hyperparameter optimization. Automated machine learning: Methods, Systems, Challenges, 3-33. doi:10.1007/978-3-030-05318-5_1
Goodwin, N.R., Armston, J.D., Muir, J.,& Stiller, I. (2017). Monitoring gully change: A comparison of airborne and terrestrial laser scanning using a case study from Aratula, Queensland. Geomorphology, 282, 195–208. doi:10.1016/j.geomorph.2017.01.001
Gutierrez, A., Conoscenti, C., Angileri, S.E., Rotigliano, E., & Schnabel, S. (2015) Using topographical attributes to evaluate gully erosion proneness (susceptibility) in two mediterranean basins: advantages and limitations. Natural Hazards, 79(1), 291–314. doi:10.1007/s11069-015-1703-0
Gutierrez, A.G., Schnabel, S., & Felicísimo, A.M., (2010). Modeling the occurrence of gullies in rangelands of southwest Spain. Earth Surface. Process. Landforms, 34(14), 1894–1902. doi:10.1002/esp.1881
Han, J., Guzman, J.A., & Chu, M.L. (2022). Gully erosion susceptibility considering spatiotemporal environmental variables: Midwest US region. Hydrology: Regional Studies, 43, 101196. doi:10.1016/j.ejrh.2022.101196
Hossain, M.D., & Chen, D. (2019). Segmentation for Object-based image analysis (OBIA): A review of algorithms and challenges from remote sensing perspective. Photogrammetry and Remote Sensing, 150, 115-134. doi:10.1016/j.isprsjprs.2019.02.009
Hosseinalizadeh, M., Kariminejad, N., Chen, W., Pourghasemi, H.R., Alinejad, M., Mohammadian Behbahani, A., & Tiefenbacher, J.P. (2019(. Spatial modeling of gully headcuts using UAV data and four best-first decision classifier ensembles (BFTree, Bag-BFTree, RS-BFTree, and RF-BFTree). Geomorphology, 329, 184–193. doi:10.1016/j.geomorph.2019.01.006
Jurchescu, M., & Grecu, F. (2015). Modeling the occurrence of gullies at two spatial scales in the Olteţ Drainage Basin (Romania). Natural Hazards, 79(1), 255-289. doi:10.1007/s11069-015-1981-6
Kirkby, M.J., & Bracken, L.J. (2009). Gully processes and gully dynamics. Earth Surface Process and Landforms. 34, 1841–1851. doi:10.1002/esp.1866
Knight, J., Spencer, J.R., Brooks, A.P., Phinn, S. (2007). Large-area, high-resolution remote sensing based mapping of alluvial gully erosion in Australia's tropical rivers. In:5th Australian Stream Management Conference, Pp.199-204. Charles Sturt University. http://hdl.handle.net/10072/18032
Kornejadi, A., Ownegh, M., Rahmati, O., & Bahremand, A. (2018). Landslide susceptibility assessment using three bivariate models considering the new topo-hydrological factor: HAND. Geocarto International, 33(11), 1155-1185. doi:10.1080/10106049.2017.1334832
Kuhnert, P.M., Henderson, A.K., Bartley, R., & Herr, A., (2010). Incorporating uncertainty in gully erosion calculations using the random forests modeling approach. Environmetrics, 21(5), 493–509. doi:10.1002/env.999
Lana, J.C. (2023). Gully erosion prediction method from geoenvironmental data and supervised machine learning techniques. MethodsX, 10, 102059. doi:10.1016/j.mex.2023.102059
Luca, F., Conforti, M., &  Robustelli, G. (2011). Comparison of GIS-based gullying susceptibility mapping using bivariate and multivariate statistics: Northern Calabria, South Italy. Geomorphology, 134(3–4), 297-308. doi:10.1016/j.geomorph.2011.07.006
Madadi, A., Saraskanroud, S.A., Negaban, S., & Marhamat, M. (2022). Evaluation of gully erosion sensitivity using maximum Entropy model in Shoor River Watershed (Mohr Township). Journal of Geography and Environmental Hazards, 11(3), 123-145. doi:10.22067/geoeh.2022.76707. [In Persian]
Manstretta, G.M.M., Perillo, G.M., & Piccolo, M.C. (2023). Gully development on the foredune of Pehuén Co (SW Buenos Aires Province, Argentina) and its relationship with rainfall and human activities. Ocean & Coastal Management, 242, 106678. doi:10.1016/j.ocecoaman.2023.106678
Mohammadi, P., Ahmadi, A., Feizizadeh, B., Jafarzadeh, A.A., & Rahmati, M. (2019). Semi-automatic object-based model to produce the inventory map of gully erosion (Case study: Lighvan watershed). Journal of Water and Soil Conservation, 26(3), 29-49. doi:10.22069/jwsc.2019.15753.3093. [In Persian]
Mokarami, M., Darvishiblorani, A., & Negahban, S.(2017). Correlation of morphometric characteristics of watersheds and erodibility at different altitude levels using topographic position index (TPI). Sepehr, 26(101), 132. [In Persian]
Movahedinasab, S., Fathabadi, A., Seydian, S.M., & Heshmatpour, A. (2019). Evolution the efficiency of random forest in gully erosion susceptibility mapping. Journal of Range and Watershed Managment, 72(1), 241-261. https://civilica.com/doc/624645/. [In Persian]
Nikpour, N., Fotohi, S., Negaresh, H., & Sistani, M. (2017). Morphometric of gully erosion and factors affecting the development of the basin plains on southern West Ilam Cham Fazel. Journal of Spatial Analysis of Environmental Hazards, 4(1), 97-112. http://jsaeh.khu.ac.ir/article-1-2696-fa.html. [In Persian]
Nyssen, J., Poesen, J., Moeyersons, J., Luyten, E., Veyret-Picot, M., Deckers, J., Haile, M., & Govers, G. (2002). Impact of road building on gully erosion risk: A case study from the Northern Ethiopian Highlands. Earth Surface Processes and Landforms, 27(12), 1267–1283. doi:10.1002/esp.404
Omidi, F., Zangiabadian, M., Shahidi Bonjar, A. H., Nasiri, M. J., & Sarmastzadeh, T. (2023). Influenza vaccination and major cardiovascular risk: a systematic review and meta-analysis of clinical trials studies. Scientific Reports, 13(1), 20235. doi:10.1038/s41598-023-47690-9
Pai, P.F., & Hong, W.C. (2007). A recurrent support vector regression model in rainfall forecasting. Hydrological Process, 21, 819-827. doi:10.1002/hyp.6323
Phillips, S.J., Anderson, R.P., & Schapire, R.E. (2006). Maximum entropy modeling of species geographic distributions. Ecological Modeling, 190(3), 231-259. doi:10.1016/j.ecolmodel.2005.03.026
Podwojewski, P., Janeau, J.L., Caquineau, S., & Hughes, J. (2020). Mechanisms of lateral and linear extension of gullies (dongas) in a subhumid grassland of South Africa. Earth Surface Processes and Landforms, 45(13), 3202-3215. doi:/10.1002/esp.4960
Pourghasemi, H.R., Yousefi, S., Kornejady, A., & Cerdà, A. (2017). Performance assessment of individual and ensemble data-mining techniques for gully erosion modeling. Science of the Total Environment, 609, 764–775. doi:10.1016/j.scitotenv.2017.07.198
Rahmati, O. (2016). Assessing the accuracy of object-based algorithm in the classification of geomorphological landforms and gully susceptibility modeling using data mining techniques (RF, SVM, ME, and BRT) in the Kashkan-Poldokhtar Watershed. Ph.D. Dissertation, University of Lorestan, Lorestan, Iran. [In Persian]
Rahmati, O., Tahmasebipour, N., Haghizadeh, A., Pourghasemi, H.R., & Feizizadeh, B. (2017). Evaluating the influence of geo-environmental factors on gully erosion in a semiarid region of Iran: an integrated framework. Science of the Total Environment, 579, 913–927. doi:10.1016/j.scitotenv.2016.10.176
Sepahvand, A., & Beiranvand, N. (2024). Landslide susceptibility mapping using various soft computing techniques (Case study: A part of Haraz Watershed). Water and Soil Management and Modeling, 4(2), 261- 278. doi:10.22098/mmws.2023.12678.1263. [In Persian]
Seutloali, K.E., Beckedahl, H.R., Dube, T., & Sibanda, M. (2016). An assessment of gully erosion along major armoured roads in south-eastern region of South Africa: a remote sensing and GIS approach. Geocarto International. 31, 225–239. doi:10.1080/10106049.2015.1047412
Shahabi, H., Amiri, Z., & Shirzadi, A. (2022). Prediction of gully erosion susceptibility and its hazards in Kloche Bijar Watershed using spatial predictive models. Environmental Hazards Management, 9(2), 89-107. doi:10.22059/jhsci.2022.348010.742. [In Persian]
Shellberg, J.G., Spencer, J., Brooks, A.P., & Pietsch, T.J. (2016). Degradation of the Mitchell River fluvial megafan by alluvial gully erosion increased by post-European land use change, Queensland, Australia. Geomorphology, 266, 105–120. doi:10.1016/j.geomorph.2016.04.021
Shiraghaei, F. (2022). Spatial variability of soil particle size distribution and aggregate stability along Upstr River of Sheikh-Lar. M.Sc. Thesis, Gorgan University of Agricultural Sciences and Natural Resources, Gorgan, Iran. [In Persian]
Tang, J., Xie, Y., Liu, C., Dong, H., & Liu, G. (2022). Effects of rainfall characteristics and contour tillage on ephemeral gully development in a field in Northeastern China. Soil and Tillage Research, 218, 105312. doi:10.1016/j.still.2021.105312
Utsumi, A.G., Pissarra, T.C.T., Rosalen, D.L., Martins Filho, M.V., & Rotta, L.H.S. (2020). Gully mapping using geographic object-based image analysis: A case study at catchment scale in the Brazilian Cerrado. Remote Sensing Applications: Society and Environment, 20, 100399. doi:10.1016/j.rsase.2020.100399
Vanmaercke, M., Poesen, J., Van Mele, B., Demuzere, M., Bruynseels, A., Golosov, V., Bezerra, JFR., Bolysov, S., Dvinskih, A., Frankl, A., Fuseina, Y., Guerra, AJT., Haregeweyn, N., IonitaI Imwangana, FM., Moeyersons, J., Moshe, I., Samani, AN., Niacsu, L., Nyssen, J., Otsuki, Y., Radoane, M., Rysin, I., Ryzhov, YV., & Yermolaev O.(2016). How fast do gully headcuts retreat? Earth-Science Reviews, 154, 336-355. doi:10.1016/j.earscirev.2016.01.009
Vrieling, A., Rodrigues, S.C., Bartholomeus, H., & Sterk, G. (2007). Automatic identification of erosion gullies with ASTER imagery in the Brazilian Cerrados. International Journal of Remote Sensing. 28(2), 2723–2738.
Wang, J.X., Fan, C.H., Zhang, Y., Li, Z., (2022). Gully head activity and its influencing factors in China’s Loess Plateau. Journal of Soils and Sediments. 28(12), 1792-1803. doi:10.1007/s11368-022-03182-3
Wang, L. (2005). Support vector machines: Theory and applications. Springer- Verlag, Pp 177. Springer Science & Business Media. New York
Yaghobi, S, Komaki, C, Hosseinalizadeh, M, Najafinejad, A, Pourghasemi, H, Faramarzi, M. (2023). Frequency Analysis of maximum daily rainfall and determining the best appropriate distribution functions in the Bostan Watershed, Golestan Province. Water and Soil Science, 27 (1), 59-81. doi:10.47176/jwss.27.1.48871. [In Persian]
Zabihi, M., Mirchooli, F., Motevalli, A., Darvishan, A.K., Pourghasemi, H.R., Zakeri, M.A., & Sadighi, F. (2018). Spatial modeling of gully erosion in Mazandaran Province, Northern Iran. Catena.161,1–13. doi:10.1016/j.catena.2017.
10.010
Zaki, A., Buchori, I., Sejati, A. W., & Liu, Y. (2022). An object-based image analysis in QGIS for image classification and assessment of coastal spatial planning. The Egyptian Journal of Remote Sensing and Space Science, 25(2), 349-359. doi:10.1016/j.ejrs.2022.03.002
Zanganeh Asadi, M.A., Naemitabar, M., & Zandi, R. (2022). Investigating the potential of erosion-prone areas with ICONA Models, support vector machine, chaid and random forest (Case Study: Gonabad Basin). Journal of Geography and Environmental Hazards, 10(4), 93-112. doi:10.22067/geoeh.2021.71162. [In Persian]