Land use land cover detections using MODIS MCD12Q1 V6.1 and ESRI Sentinel-2 datasets in the Lake Chamo catchment

The land use and land cover (LULC) changes are a dynamic and complex process that can be caused by both anthropogenic and natural factors (Birhanu et al. 2019; Samal & Gedam 2021). The primary drivers of LULC changes have been carried out by human activities (Betru et al. 2019; Dibaba et al. 2020). For the past 1,000 years, human beings have been altering LULC to obtain livelihoods and other necessities. The amount, rate, and severity of LULC change are significantly higher now than they were previously particularly in the developing nations, whose economies are mainly based on agriculture (Hassan et al. 2016). It is well understood that the LULC change can alter regional hydrological conditions, which may further result in a variety of impacts on the water resource system (Li et al. 2007). Human activities including societal development, overgrazing, the inappropriate utilization of forest, agricultural land expansion and increasing population have all contributed to a substantial increase in LULC which leads to simultaneous changes in natural environments, ecosystem services and hydrological change (Zewdie & Csaplovies 2015; Samal & Gedam 2015).

Many factors influence land use and cover changes, including time, scale, politics, economic, social, and cultural factors (Calicioglu et al. 2019). At all spatiotemporal scales, LULC changes have been recognized as significant drivers of environmental changes (Adepoju et al. 2006). Such changes, along with other negative changes (e.g., climate change, biodiversity loss, and water, soil, and air pollution), should be the top priorities for humans (Zabihi et al. 2020). Therefore, updated and precise LULC maps are essential for sound planning, sustainable development, environmental monitoring, worldwide change, the evaluation of forest degradation, and water resource management (Dewan & Yamaguchi 2009). The effective use and management of natural resources depends on the result of land use and land cover changes. Therefore, international researchers have put considerable effort into studying land-use land cover using different approaches, and it is better to evaluate the land-use land cover change of Lake Chomo catchment for sustainable lake water management and maintain the ecosystem of the catchment.

The land cover land use dynamics in Ethiopia have changed with an increasing population, due to its economy largely depending on agriculture and land use. Land cover conditions are considerably changing (Getachew & Melesse 2012; Berihun et al. 2019; Aredo et al. 2021). Specifically, shrub lands, bare lands, forest covers and grasslands (GLs) were converted to settlement and agricultural lands in many parts of the country (Tadele & Förch 2007; Rientjes et al. 2011; Gumindoga et al. 2014; Andualem & Gebremariam 2015; Jemberie et al. 2016). Rising rates of urbanization and agricultural land at the cost of natural vegetation have significant influence on the hydrological responses of a basin. LULC also has a significant influence on the hydrological fluxes due to variations in the physical characteristics of the land surface and soil, such as roughness, architectural resistance, stomatal conductance, albedo, leaf area index (LAI), root depth, and infiltration capacity (Maza et al. 2020; Srivastava et al. 2020). Disturbance of vegetation and the subsequent change to other land-use land cover classes are known to have multiple impacts on land productivity, stream flows, geomorphological processes and the socioeconomic status of the river basin. The effect changes from basin to basin based on the extent and intensity of the natural land cover conditions and characteristics (Samal & Gedam 2021). Changes in LULC availability and distribution have a substantial influence on climate, environmental challenges, and natural ecosystem conditions (Cihlar 2000; Yan et al. 2015). Furthermore, changes in global LULC are a major cause of significant concern for future LULC trends (Prestele et al. 2016; Karki et al. 2018). Additionally, LULC changes are a critical aspect of sustainability and management of natural resources (Degife et al. 2018; Hou et al. 2019; Motlagh et al. 2020). The Lake Chamo catchment is one of the rift valley sub-basin and is found in a semi-arid and drought-prone region in Ethiopia (MoWE 2007). Due to an increasing population, human activities have been increasing rapidly in the catchment, like deforestation, increasing agricultural farm land, which leads to climate change, environmental conservation, environmental pollution and soil erosion, which affect economic development to meet food and housing requirements. Additionally, several studies have been conducted on LULC dynamics in Ethiopia at a basin level (Simane et al. 2013; Teklu & Kassahun 2017; Wondie 2018; Giweta & Worku 2018). But, to the present, no such investigation has been available in existing literature for Lake Chamo Catchment. Therefore, understanding and identifying detailed historical LULC dynamics knowledge over a lengthy series of periods and analyzing their patterns and processes is critical in the lake basin for land development decision-makers and planners.

Geographic information system (GIS) and remote sensing (RS) techniques provide helpful approaches for understanding, analyzing, and monitoring LULC over time in landscapes (Kotaridis & Lazaridou 2018; Armin et al. 2020). Many investigations on LULCs have been conducted using these tools (Hua 2017; Mannan et al. 2019). Zhou used an integrated approach to detect the changing green spaces pattern 3 and identified that the change was caused by fast urbanization and greening programs (Zhou & Wang 2011). Different satellites deliver historical images that can be used to evaluate the effects of human and other elements over time (Goldblatt et al. 2016; Gomez et al. 2016; Haque & Basak 2017). Additionally, Landsat periodic imagery data for a specific area is a reliable data source that can be utilized to forecast LULC trends in that area. GIS and RS techniques are effective for displaying spatial modeling methods (Nouri et al. 2014). Thus, modeling, simulation, and predicting LULC changes using temporal and spatial data are crucial for improving LULC planning and management. Although the complexity of developing models and simulations is great, they are necessary to detect the LULC changes and analyze the causes and consequences of this phenomenon (Yang et al. 2012). Furthermore, various approaches for determining historical and prospective LULC have been established to assist stakeholders in economic improvement, land conservation, and land-use planning. In addition, several models for simulating future scenarios of LULC have been created. These models deliver appropriate approaches for detecting the spatial variability patterns in LULC. Moreover, model validation is required for an accurate assessment of LULC prediction in a particular area by comparing predicted and observed LULC changes (Nath et al. 2020).

In the Lake Chamo catchment, LULC change is a common phenomenon. This continuous change in land cover land use has an impact on the lake ecosystem by altering the magnitude and pattern of hydrological variables, increasing soil erosion, thereby exacerbating the water management problem. To the best of the author's knowledge, detail and quantitative analysis have not yet been conducted in Lake Chamo catchment, which has already faced many changes due to increased farming and deforestation. There appears to be a gap in the available information and national decision-making process and rational planning in water resource monitoring and ecological restoration of Lake Chamo catchment. Generally, this study aims to evaluate the patterns of LULC changes in expanding agricultural area in the Lake Chamo catchment. The main focuses of this study are: (1) to identify the LULC based on satellite images of the years 2001 and 2022 using RS and GIS application, (2) to evaluate the LULC changes in Lake Chamo catchment between 2001 and 2022 in a quantitative manner, (3) to calculate the factors of the LULC change in the study area. This study is expected to contribute to the decision making in enabling a better emergency response and plan toward sustainable land development activity as well as mitigating the challenges of the rapid growth of agricultural land and deforestation. The adopted approaches for long-term variability of LULC and its result will be regarded as a new and honest contribution to the Chamo basin.

Lake Chamo catchment is located in the southern part of Ethiopia (Figure 1). It is located between the latitudes of 5°3′54″ and 6°03′57″ N and the longitude of 37°15′18″ and 37°40′37″E. The catchment area is 1,867 kilometers square. The third-largest rift valley lake called Lake Chamo was located in this catchment, which is essential for fisheries, agriculture, and tourism. The elevation of the study area ranges from 1,108 to 3,380 meters above mean sea level. The mean precipitation of the study area ranges from 0 to 291.23 mm per month. The average temperature ranges between 12.6 and 34.1 °C.

Remotely sensed and spatial data are trustworthy data for detecting and comprehending the dynamic causes of LULC in any terrain (Hansen et al. 2000). RS data acquisition involves collecting information about the Earth's surface without physically being there. This is usually done by using instruments such as satellites, airplanes, drones, or ground-based sensors to capture images, spectra, and other data. The type of instrument used depends on the spatial and spectral resolution required for the specific application. Satellites are used for large-scale mapping, while drones are used for high-resolution imaging of specific areas. Data acquisition can involve active or passive sensing, with active sensors emitting energy and measuring its reflection, while passive sensors measure the energy emitted by the Earth's surface. For this study, remote sensing images of NASA LPDAAC collection of MODIS Land Cover-V6.1 (MODIS MCD12Q1 V6.1) from the Earth explorer site (https://earthexplorer.usgs.gov, accessed on 25 July 2024) at a location of 05O58′ 20″ N latitude and 037O 31′ 49″ from 2001 to 2022 and used for LULC classification. The satellite images that were collected by USGS earth explorers provide many kinds of satellite imagery for free. Cloud-free images are not easy to find using free sources of data, so no more than 10% of cloud cover was applied in the additional criteria tab while searching and about 4–6% of cloud covers were found, which did not affect the result of LULC classification. The datasets were downloaded as HDF files and imported in to ArcGIS 10.4. To minimize errors due to different seasonal variation in vegetation distribution or in LULC change detection, images of the same annual season were used (Kindu et al. 2013; Dibaba et al. 2020).

Preprocessing was essential to increase visual interpretation and spectral separability of earth surface characteristics, as well as provide improved inputs for automated image processing algorithms (Maini & Aggarwal 2010). For this study, the downloaded images were pre-processed in ArcGIS 10.4. This approach produces adjusted satellite images that are radio-metrically and geometrically corrected (Lillesand et al. 2015). Radiometric corrections are generally used to normalize multi-temporal satellite images for time-series comparisons. The true band of the image was extracted by using the extraction algorithm of ArcGIS 10.4 spatial analyst tool.

The number of classes in the image is indicated by IJ. C_ij indicates how much class IJ has changed. (P_ij) is the percentage change in class IJ. X_i is ‘basic image’ (20001). The most current picture is X_j (2022).

The index is easy to interpret: NDVI will be a value between −1 and 1. An area with nothing growing in it will have an NDVI of zero. NDVI will increase in proportion to vegetation growth. An area with dense, healthy vegetation will have an NDVI of one. NDVI values less than 0 suggest a lack of dry land. An ocean will yield an NDVI of −1.

NIR, Red, and Blue are atmospherically-corrected and partially atmosphere-corrected (Rayleigh and ozone absorption) surface reflectances.

L is the canopy background adjustment that addresses non-linear, differential NIR and red radiant transfer through a canopy.

The coefficients adopted in the MODIS-EVI algorithm are as follows: L = 1, C₁ = 6, C₂ = 7.5, and G = 2.5.

EVI is similar to the NDVI and can be used to quantify vegetation greenness. However, the EVI corrects for some atmospheric conditions and canopy background noise and is more sensitive in areas with dense vegetation.

In the present study, the LULC was evaluated for the last 22 years, from 2001 to 2022. Based on the spectral characteristics and MODIS MCD12Q1 V6-1, the study area was classified as EBF, Sav, GLs, PWLs, CLs, VMs, BL, and WBs. The details of long-term LULC change for each land cover type have been described in the following. This finding is in line with earlier, similar studies (Elagouz et al. 2019; Kamel 2020; Mohamed et al. 2020; Said et al. 2020; Abd El-Hamid et al. 2022).

The accuracy of classified images was assessed by evaluating the UA, PA, OA and kappa coefficients for the years 2001, 2010, and 2022. Table 1 shows the summarized LULC classification accuracy for 2001, 2010, and 2022. Based on the estimated results, the OAs of the classified images for the years 2001, 2010, and 2022 were 88.4, 89.1, and 91.4%, respectively. The OA of the classified images exceeded the minimum recommended accuracy of 85%, which shows high accuracy and reliability for LULC dynamics evaluation and consistent with related studies (Anderson et al. 1976). For the years 2001, 2010, and 2010, the kappa statistics of the LULC were 0.86, 0.91, and 0.88, respectively, showing that the agreement between the identified LULC classes and the geographical data is strong. Based on Viera and Garrett (2005), the kappa value higher than 0.8 indicates strong agreement, whereas kappa values ranging between 0.61 and 0.8 demonstrate very good agreement and the result of the kappa value for this study was higher than that of the recommended value. Additionally, the kappa values were described as a considerable agreement to near perfect agreement, which agrees with similar studies (Irwin et al. 2009). The results for OA, producer accuracy (PA), user accuracy (UA) and kappa coefficient were presented in Table 1. The classification images are valid for evaluation using ground truth for land cover dynamics evaluation.

The current study was carried out to assess variation in LULC type in Lake Chamo catchment using MODIS and ESRI data in ArcGIS 10.4. The study area was classified as EBF, Sav, GLs, PWLs, CLs, VMs, BL and WBs for MODIS data, whereas for ESRI dataset water, trees, flooded vegetation, crops, built area, bare ground and rangeland/savanna were identified. The OA of the classified images for the years 2001, 2010, and 2022 were 88.4, 89.1, and 91.4%, whereas the kappa statistics of the LULC were 0.86, 0.91, and 0.88, respectively, for MODIS datasets. The OA and kappa coefficient of LULC for the ESRI-based land use classification was 98.0 and 97.8%, which is higher than the threshold of accuracy reported by similar studies (Irwin et al. 2009). Based on Viera and Garrett (2005), the kappa value higher than 0.8 indicates strong agreement, whereas kappa values ranging between 0.61 and 0.8 demonstrate very good agreement and the result of the kappa value for this study was higher than that of the recommended value. Additionally, the kappa values were described as a considerable agreement to near perfect agreement and are consistent with similar studies (Irwin et al. 2009). The result for producer accuracy and user accuracy was presented in Table 1 for each LULC class of MODIS dataset. Concerning the accuracy assessment of the used dataset, a producer accuracy and user accuracy of greater than 76% was obtained in all years for MODIS dataset. The results revealed that GL was the major LULC for MODIS dataset, whereas crop land was the dominant LULC type for ESRI datasets. Built-up areas and crop land show an increasing trend in the ESRI dataset due to increasing populations. For MODIS dataset, fluctuations in LULC type were observed during the study period. The rate of change of WBs for ESRI dataset were 16.64, 16.66, 16.66, 17.19, and 17.88% from 2017 to 2021, respectively, trees were 12.19, 11.07, 9.75, 19.91, and 9.84%, flooded vegetation were 0.04, 0.15, 0.11, 0.72, and 0.68%, built-up area (1.75, 1.86, 1.83, 2.31, and 2.38%), bare ground (0.08, 0.12, 0.15, 1.25, and 0.11%), crops (29.88, 37.3, 39.48, and 41.94) and rangeland/Savanna (39.41, 32.83, 29.56, 19.15, and 28.06%), respectively, from 2017 to 2021. For MODIS dataset the rate of change of EBF was 0.06, 0.04, 0.11, 0.11, and 0.08%, Sav (20.55, 23.38, 19.62, 19.62, and 23.21%), G (44.54, 43.47, 42.53 42.53, and 46.13%), PWL (2.1, 2.17, 2.05, 2.05, and 2.89%), crop lands (17.45, 15.51, 20.30, 20.30, and 11.59%), NVM (0.13, 0.26, 0.15, 0.15, and 0.48%), B (0.35, 0.32, 0.33, 0.33, and 0.26%), WB (14.83, 14.85, 14.91, 14.91, and 15.36%). Furthermore, the most considerable increase and decrease in LULC type was observed during the study period for the study area. This variation in LULC type was due to human interventions, which are mainly based on agricultural development, due to an increasing population and other activities. The study area is inhabited by rural people in which their livelihood depends on agriculture and thus the natural growth is relatively higher than urban areas. Currently, the population of the study area has increased and its effect on the environment and water resources is devastating. Due to population growth, farm land owned by the parents is continuously shared by the number of children and, therefore, land fragmentation continues. On the other hand, its size is desolately declining. This has caused natural resource scarcity and has supported natural resource degradation in the study area. Moreover, population growth results in cultivated land expansion at the expense of natural vegetation and grazing in the study area. This finding is similar to recent studies conducted in other parts of Ethiopia, which demonstrate that population growth is the main cause of the LULC change (Bewket 2003; Asmamaw et al. 2011; Gebru 2016). Due to this, different land uses compete with one another, and can reduce the quality of natural resource bases and land productivity, including water resources. Agricultural growth is still based on areal expansion (Abate 2011) and thus, there was mismanagement of land, including cultivating steep slopes and marginal land, overgrazing and destruction of forest for different purposes. On the other hand, the livelihoods of many people in the study area rely on the sale of firewood, charcoal and other things. In recent years, firewood and charcoal have become the most commercialized energy sources for both the rural and urban communities in the area, which is similar to the finding conducted in the sub-basin of the upper Blue Nile in north Gojjam (Ewunetu et al. 2021). So, the human driving forces such as all forms of formal and informal activities were the major cause of LULC variation in the study area and consistent with similar studies (Naidoo 2005; Monteiro et al. 2018). Generally, the main causes of LULC changes in the study area include population pressure, agriculture and settlement expansions to marginal mountain areas, increasing wood demand for fuel, collection of farm implements and construction wood, charcoal production, livestock grazing and others. Landforms are also the main factors influencing land use/cover diversity and patterns. The topographic factors such as elevation, aspect and slope change the water and heat supply of vegetation and the physical and chemical conditions of soil, which led to the change in LULC and is consistent with similar studies (Hoylman et al. 2018; Chen et al. 2021). Similarly, climate change directly and indirectly affects LULC and the ecosystems by altering the pattern, distribution and practice of land, which was also reported by similar studies (Turner & Gardner 2015; Monteiro et al. 2018; Guo et al. 2020; Erdös et al. 2022; Acharki et al. 2023). LULC changes such as deforestation, cultivated land expansion and urbanization also have a long-term impact on hydrological processes such as stream flows, evapotranspiration (ET), groundwater recharge, surface water availability, leaching and infiltration rate, which affects water resource availability and also agrees with similar studies (Loveland & Mahmood 2014). Additionally, LULC change and its dynamics are directly related to biodiversity and productivity of land and have enormous environmental and societal impacts which affect both local and global systems by altering the interaction of energy, greenhouse gases and water between land and the atmosphere (Sleeter et al. 2017). Hence, sustainable land use planning and management should be put in place for local communities, with particular emphasis on close supervision of bare land restoration, forest and bush land conservation, making grazing lands available through restoration of degraded land and regulating further expansion of areas under cultivation. A people-centered approach to the integration of conservation of the natural resource base (water, soil, trees and local biodiversity) and development to overcome natural resource degradation was a key strategy recommended in this study. This community-based conservation and resource management system uses new beliefs about the suitability of communities to suggest policy recommendations. The implicit assumption behind these recommendations is that communities have incentives to use unsustainable resources when they are not involved in resource management. If communities are involved in conservation, the benefits they receive will create incentives for them to become good stewards of resources. Measures to address water availability in the Lake Chamo catchment include: Setting up the appropriate institutional and legal framework for comprehensive water management; building capacity and raising awareness of water resources and other natural resource management at all levels; creating effective monitoring systems for ground and surface water resource assessment. The natural degradation and soil erosion is common in the study area, which leads to sedimentation of the lake and affects the lake ecosystem and needs awareness for lake water management. Government policies and institutions also must be aware of the rapid land use changes to maintain or enhance natural resource management and sustainable economic development. Additionally, yearly variation of LULC for each land use type was evaluated and change was detected in the year of the study period from 2001 to 2022 and the result revealed that savanna and GL were the dominant LULC in the study area during the study period. The investigation has shown that changing land use and land cover was a pervasive, rapid, and significant trend in the study area during the study period. This study gives valuable information to policy-makers and stakeholders for sustainable economic development, lake water management, ecological maintenance and climatic change adoption pathways in the study area. Based on the estimated result, the monthly values of EVI, NDVI, and NDWI ranged between 0.114 and 0.383, 0.142–0.41, and 0.066–0.29, respectively, whereas the yearly values of EVI, NDVI, and NDWI ranged between 0.129 and 0.278, 0.155–0.326, and 0.09–0.217, respectively, from 2013 to 2023. This investigation has shown that the monthly and yearly values of NDWI were less than 0.3 during the study period and shows a significant variation for the study period. The NDVI and EVI were used to quantify vegetation greenness and NDWI was used to delineate and monitor surface water content, which agrees with similar studies (Li et al. 2010). Changing land use types provides immediate economic benefits for the community but dramatically alters or causes imbalances in ecosystem services, including water availability. For example, the conversion of GL and forest to CL and built-up area is expected to have an impact on the hydrological cycle, increasing soil erosion and runoff. This, in turn, leads to the deterioration of ecological services, which may have an impact on the local community's livelihood. Proper GL, forest, and shrub-bushland management is critical for the long-term viability of water availability and climate change. Appropriate LULC management was essential for the long-term variability of climate change in the study area and ecological restoration of the lake catchment. Understanding and managing LULC changes is also crucial for addressing environmental challenges, promoting efficient utilization of natural resources, sustainability of environmental and ecological systems for the well-being of both present and future generations. Generally, the results of the study revealed a substantial change in land cover use in the study area over the period (2001–2022). The findings recommend that major stakeholders, including environmental protection agencies, forest guides, water resource organizations and municipal assembly authorities, should develop feasible holistic preventive measures that seek to ensure effective and efficient utilization of resources and promote the livelihoods of individuals who depend on these resources for survival.

This study was carried out in the Lake Chamo catchment to evaluate LULC variation based on MODIS MCD12Q1 V6.1 and ESRI Sentinel-2 datasets on spatiotemporal changes. Multi-temporal satellite imagery can provide the essential measurement of spatial and temporal phenomena for areas where it is difficult to evaluate LULC using traditional mapping. Therefore, this study focused on detecting and analyzing LULC changes in the study area over the different periods examined from 2002 to 2022. The estimated result shows that 8 land-use land cover types were observed for MODIS MCD12Q1 V6.1 dataset, while 7 land-use land cover types were obtained for ESRI Sentinel-2 dataset in the study area during the study period. The result shows a significant variation in LULC changes for the study area during the study period. Based on the accuracy assessment, the OAs of the classified images in the years 2001, 2010, and 2022 were 88.4, 89.1, and 91.4%, whereas the kappa statistics of the LULC were 0.86, 0.91, and 0.88, respectively. The spatiotemporal variation of LULC from MODIS MCD12Q1 V6.1 shows that the savanna LULC type accounts for 29.45, 27.63, and 22.18%, respectively, in the years 2001, 2010, and 2022, respectively. The changes in EBF were 0.1, 0.05, and 0.08% for the years 2001, 2010, and 2022, respectively. The changes in PWL were 2.03, 1.51, and 2.69% in the years 2001, 2010, and 2022, respectively. The variation in crop land was 12.82, 7.74, and 9.25% for the years 2001, 2010, and 2022, respectively. The changes in NVM were 3.77, 0.51, and 0.08% for the years 2001, 2010, and 2022, respectively. The variation in bare land was 0.21, 0.54, and 0.31% for the years 2001, 2010, and 2022, respectively. The change in body water was 15.65, 14.68, and 15.52% for the years 2001, 2010, and 2022, respectively. The Sentinel-2 LULC type shows that 310.18 km² (16.64%), 227.28 km² (12.19%), 0.80 km² (0.04%), 556.95 km² (29.88%), 32.54 km² (1.75%), 1.54 km² (0.08%) and 734.49 km² (39.41%) for the 2017, 310.53 km² (16.66%), 206.28 km² (11.07%), 2.83 km² (0.15%), 695.24 km² (37.3%), 34.63 km² (1.86%), 2.33 km² (0.12%) and 611.94 km² (32.83%) in the year 2018, 310.45 km² (16.66%), 181.78 km² (9.75%), 2.04 km² (0.11%), 781.69 km² (41.94%), 34.08 km² (1.83%), 2.80 km² (0.15%) and 550.93 km² (29.56%) in the year 2019, 320.34 km² (17.19%), 371.01 km² (19.91%), 13.38 km² (0.72%), 735.74 km² (39.48%), 43.07 km² (2.31%), 23.27 km² (1.25%) and 356.95 km² (19.15%) in the year 2020, 333.16 km² (17.88%), 183.32 km² (9.84%), 12.72 km² (0.68%), 765.33 km² (41.06%), 44.27 km² (2.38%), 2.04 km² (0.11%) and 522.92 km² (28.06%) in the year 2021 for water, trees, flooded vegetation, crops, built area, bare ground and rangeland/savanna, respectively. According to the result, the degree of LULC change can effectively reflect the breadth and depth of development. The monthly values of EVI, NDVI, and NDWI ranged between 0.114 and 0.383, 0.142–0.41, and 0.066–0.29, respectively, whereas the yearly values of EVI, NDVI, and NDWI ranged between 0.129 and 0.278, 0.155–0.326, and 0.09–0.217, respectively, from 2013 to 2023.

The increased population and agricultural activities in the lake basin area have a considerable impact on LULC types. Additionally, natural factors such as change in climate, land forms, and soil type affect the LULC type. This investigation has shown that changing land use and land cover is a pervasive, rapid, and significant trend in Lake Chamo catchment. The findings of the current study provided evidence that MODIS MCD12Q1 V6.1 and ESRI Sentinel-2 datasets are an effective dataset used for detecting LULC variation in the study area and also can be used in different areas. The result of the study demonstrates that the policy-makers and stakeholders of the Lake Chamo catchment need to be conscious of the rapid change of land use which affects the lake water body. Therefore, it concludes that a major land use was identified, and the increasing population is a driving factor to trigger the transformation of the study area during the study period.

Conceptualization, methodology, original draft writing, preparation, and development of model was done by A.K.Y.

The author approved that this article is new and original, and not published in any other journal.

We agree to participate in the journal.

The author agrees to publish the journal.

Data cannot be made publicly available; readers should contact the corresponding author for details.

The author declares no competing interests.