RESEARCH ARTICLE Assessment of land cover and land use change impact on soil loss in a tropical catchment by using multitemporal SPOT‐5 satellite images and Revised Universal Soil Loss Equation model Haleh Nampak 1 | Biswajeet Pradhan 2,3 | Hossein Mojaddadi Rizeei 2 | Hyuck‐Jin Park 3 1 Discipline of Geospatial and Spatial Sciences, School of Technology, Environments and Design, University of Tasmania, Hobart, TAS 7000, Australia 2 The Centre for Advanced Modelling and Geospatial Information System (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, 2007 NSW, Australia 3 Department of Energy and Mineral Resources Engineering, Choongmu‐gwan, Sejong University, 209 Seoul, Republic of Korea Correspondence Biswajeet Pradhan, The Centre for Advanced Modelling and Geospatial Information System (CAMGIS), Faculty of Engineering and Information Technology, University of Technology Sydney, 2007 Sydney, NSW, Australia. Email: biswajeet24@gmail.com; biswajeet. pradhan@uts.edu.au Funding information UTS, Grant/Award Number: 321740.2232335 321740.2232357; Korea government (MSIP), Grant/Award Number: NRF‐ 2016R1A2B4008963 Abstract Soil erosion is a common land degradation problem and has disastrous impacts on nat- ural ecosystems and human life. Therefore, researchers have focused on detection of land cover–land use changes (LCLUC) with respect to monitoring and mitigating the potential soil erosion. This article aims to appraise the relationship between LCLUC and soil erosion in the Cameron Highlands (Malaysia) by using multitemporal satellite images and ancillary data. Land clearing and heavy rainfall events in the study area has resulted in increased soil loss. Moreover, unsustainable development and agricultural practices, mismanagement, and lack of land use policies increase the soil erosion rate. Hence, the main contribution of this study lies in the application of appropriate land management practices in relation to water erosion through identification and predic- tion of the impacts of LCLUC on the spatial distribution of potential soil loss in a region susceptible to natural hazards such as landslide. The LCLUC distribution within the study area was mapped for 2005, 2010, and 2015 by using SPOT‐5 temporal sat- ellite imagery and object‐based image classification. A projected land cover–land use map was also produced for 2025 through integration of Markov chain and cellular automata models. An empirical‐based approach (Revised Universal Soil Loss Equation) coupled with geographic information system was applied to measure soil loss and sus- ceptibility to erosion over the study area for four periods (2005, 2010, 2015, and 2025). The model comprises five parameters, namely, rainfall factor, soil erodibility, topographical factor, conservation factor, and support practice factor. Results exhib- ited that the average amount of soil loss increased by 31.77 t ha -1 yr -1 from 2005 to 2015 and was predicted to dramatically increase in 2025. The results generated from this research recommends that awareness of spatial and temporal patterns of high soil loss risk areas can help deploy site‐specific soil conservation measures and erosion mitigation processes and prevent unsystematic deforestation and urbaniza- tion by the authorities. KEYWORDS Cameron Highlands, GIS, LCLUC, remote sensing, soil loss estimation 1 | INTRODUCTION Spatiotemporal changes in land cover–land use (LCLU) are regarded as an important factor responsible for environmental modification worldwide. Detection of LCLU changes (LCLUC) is initially required for evaluating latent environmental impacts and developing land management strategies. Some researches have studied the LCLUC associated with land degradation and desertification (Biro, Pradhan, Received: 28 December 2017 Revised: 10 July 2018 Accepted: 22 July 2018 DOI: 10.1002/ldr.3112 3440 © 2018 John Wiley & Sons, Ltd. Land Degrad Dev. 2018;29:3440–3455. wileyonlinelibrary.com/journal/ldr