Land Cover Change Studies Research Articles

A study of land cover and land surface temperature changes triggered by tropical cyclone "Titli".

The intensity and frequency of tropical cyclones (TC) are on the rise due to climate change, resulting in severe damage to coastal regions. Hence, the mitigation of socioeconomic and environmental consequences of cyclones has attained paramount importance in the recent years. In this study, the rapid impact of a very severe cyclonic storm "Titli" on land cover (LC) changes were evaluated using Moderate Resolution Imaging Spectroradiometer (MODIS) and high-resolution Sentinel-2 data. The cyclonic event caused substantial modifications in land use and land cover with nearly 46% decrease in dense vegetation, 129% increase in fallow land, and 111% increase in water body, over the study region. Widespread damage (dense to less dense vegetation) was evident on the left side of the cyclone track as compared to the right. The analysis revealed a 98.3% decrease in dense vegetation, marked by a decrease in the normalized difference vegetation index (NDVI) from 0.73 to 0.44 over the landfall region. This NDVI decrease continued for nearly 3months before the onset of vegetation regrowth. Change in vegetation into other LCs over the landfall region resulted in an increase of the mean daytime land surface temperature by ~ 6°C. The analysis highlights the magnitude of spatiotemporal scale damages to LULC and consequent loss in seasonality that can be ushered in by a single short-duration extreme weather event like TC and thus emphasizes the need for well-formulated mitigation strategies.

Study on Vegetation Coverage Based on Binary Pixel Model

Vegetation coverage (FVC) is an important indicator of ecosystem change and provides an indicator for the study of land cover change. In this paper, taking Zhengzhou City as an example, the 2015 Landsat 8 OLI remote sensing images were used as data sources, normalized vegetation index (NDVI) was used as a parameter to extract information from the study area, and the pixel binary model was used to calculate vegetation coverage. The results showed that the vegetation cover was higher in the west and lower in the east, and some forest land was changed into cultivated land from west to east.

Internal and edge-effect environmental monitoring to assess the threats facing intact tropical peat swamp forest in Central Kalimantan

Peat swamp forest (PSF) provides vital environmental benefits, including carbon storage. However, almost half of the Indonesia’s PSF areas are extensively degraded. Internal threats such as drainage contribute to peat drying, vegetation damage and heightened fire risk. Equally, forest edges are threatened from human activity and fire spread, leading to forest edge regression. This study assesses biophysical changes within an area of intact tropical PSF and along their edges in Central Kalimantan. To assess these threats, we established seven transects perpendicular to the forest edge, transitioning from degraded to intact forest. Forty-nine dipwells, and three loggers were installed to assess drainage and subsidence. We established seed traps and seedling plots along three transects at three distances from the forest edge (three replicates per distance) to assess forest edge regeneration potential. Furthermore, we are analysing historic remote sensing data from the last two decades to study land cover change and forest edge loss related to fire. Equipment was established February 2022, with data collection underway for 12 months. Here, we present our initial findings. The results will provide quantitative and qualitative data analysis to describe potential threat levels facing this forest and give recommendations for developing a targeted conservation action plan.

Land Use and Land Cover Change Study Using RS-GIS and Its Impact on Biodiversity: Study from Arunachal Pradesh, India

This study aims to depict the intricate relationship between biophysical parameters, particularly land surface temperature (LST), and their impact on biodiversity at Itanagar Wildlife Sanctuary in Arunachal Pradesh. Focused on the consequences of anthropogenic activities, our research assesses changes in forest cover using Landsat images from 1990, 2003, and 2019. Utilizing satellite data, calculation of indices such as Normalized Difference Vegetation Index (NDVI), Normalized Difference Built-up Index (NDBI), Normalized Difference Water Index (NDWI), and LST were performed. Land use land cover (LULC) was determined through supervised classification, achieving accuracies of 75%, 87%, and 83% for 1990, 2003, and 2019, respectively. The analysis highlighted a substantial increase in settlement area from 9.37 km2 in 1990 to 22.86 km2 in 2019, indicative of significant urbanization impacts.Our findings reveal a pronounced positive correlation between settlement growth and elevated LST, indicating the influence of urbanization on thermal dynamics. Additionally, positive correlations were observed between LST and NDBI, while a negative correlation existed between LST and NDVI. Questionnaire-based surveys complemented remote sensing data, exposing a gradual decline in wildlife sightings, diminishing populations of rare plant species, and the proliferation of invasive plants within and around the Wildlife Sanctuary since 1990.This research underscores the substantial impact of urbanization on the biodiversity of the Itanagar Wildlife Sanctuary. Positive correlations between settlement growth, LST, and biophysical parameters emphasize the urgency for targeted conservation strategies. The decline in wildlife sightings and the encroachment of invasive species underscore the need for proactive measures to balance biodiversity conservation with the challenges posed by urban development. Our integrated approach, combining remote sensing, survey data, and ecological indices, offers valuable insights for sustainable management and conservation efforts in similar habitats globally.

The nature of a ‘forest transition’ in Thừa Thiên Huế Province, Central Vietnam – A study of land cover changes over five decades

Informed from historical case studies of land cover change and development in northern countries, forest transition (FT) theories have a tendency to precast specific conclusions. Considering the case of a so-called FT in Thừa Thiên Huế Province in tropical Central Vietnam, we investigated 1.) whether such a ‘FT’ indeed reflects a resurgence of genuine forest, 2.) whether the land cover changes can be explained through conventional ‘pathways’ of FT, and 3.) in which ways the changes may or may not portend ‘sustainable development’. Using satellite imagery and topographic maps, we produced maps for twenty land cover types for the years 1966, 1973, 1979, 1988, 1998, 2008, 2016 and 2019 and analysed land cover change over time. We contextualize these results with reference to the historical and scientific literature on Vietnam, and find that 1.) the forestlands represent a historically rich bio-cultural landscape; 2.) considerable forest destruction resulted from the Second Indochina War rather than classical degradation pathways; 3.) in the post-war period altered forestland spaces and re-emerging land uses interacted with state-led re-territorialization and socialist plans for land resource development, influencing shifts in forest cover; 4.) during 1979–1988 state-led intensive timber logging in remaining rainforests (causing widespread forest degradation) somewhat paradoxically (in terms of conventional FT models and theories) coincided already with a slight increase in lower-biomass tree cover; 5.) after 1988 logging in natural forests was officially prohibited (logging bans), and forestry shifted to a reliance on wood produced in acacia-based plantations (largely on lands officially allocated to households); and 6.) this shift went along with a significant state-led restructuring and development of land use policies and the promotion of forest-relevant economic industries. ‘Restoration’ of tree cover mainly consisted of the expansion of exotic tree plantations, but – at least intermittently – this may also have mitigated impacts on natural forests. We conclude with some reflections on the FT-outcome, its ‘sustainability’, and future trajectories and possibilities of land cover changes in TTHP.

Downscaling of vegetation indices from multi-satellite throughout-season maize

Phenomenology of the growing season The Normalized Difference Vegetative Index (NDVI) provided by satellites was employed as a replacement for quantifying the output of vegetative biomass. The MODIS sensors 250-m data have been utilized for terrestrial ecosystem modelling and monitoring. MODIS’s land surface data are credible and trustworthy because to their high temporal resolution and broad spectrum of wavelengths. Land cover and land change studies have used the spatially accurate data provided by the Landsat 30m to characterize human-scale processes. Sentinel-2 is a land surveillance satellite with innovative spectrum capabilities, extensive coverage, and excellent spatial and temporal resolutions. The primary purpose of this work is to create a downscaling vegetation indices (VI) database by combining MODIS, Landsat, and Sentinel data into 250m resolution. The most important NDVI indicates the maize growing season in April and August. MODIS, Landsat, and Sentinel 250m derived biophysical information deliver the same biophysical information for moderate-scale biological aspects. This multi-sensor inquiry also includes high-resolution Landsat data, which will be useful for local ecological investigations while keeping the full seasonal dynamic information given by MODIS.

A Multi-Temporal Analysis of Archaeological Site Destruction using Landsat Satellite Data and Machine Learning, Moche Valley, Peru

The destruction of archaeological sites and the loss of archaeological landscapes remains a global concern as populations and urban areas continue to expand. Archaeological sites are not only significant to local communities, national identities, and modern tourist economies but also provide critical knowledge of past sociocultural interactions, settlement patterns, human-environment relationships, and risk mitigation strategies. While archaeological landscapes and site destruction have remained outside of traditional land use land cover change (LULCC) studies, they are a form of urban and agricultural land use. By conceptualizing archaeological site destruction within land change science, this study provides an innovative approach for assessing “what's left” of historically surveyed archaeological landscapes. Using a Random Forest algorithm and Landsat satellite data, this study quantifies archaeological site destruction attributed to LULCC in Peru's lower Moche Valley between 1985 and 2020. More than 400 archaeological sites previously recorded during the Chan Chan-Moche Valley Project (CCMVP, 1969–1974) are analyzed. Results indicate that less than a quarter of the original CCMVP sites remain on the landscape. The primary drivers of LULCC in the lower Moche Valley include population growth, migration, and government policies, while secondary drivers include heritage values. Positioning archaeological survey data within land change science and integrating machine learning techniques can benefit historic survey reassessments globally and provides significant knowledge of archaeological site destruction and the socioeconomic conditions that underly dynamic landscape changes.

The use of computer tablets in sociodemographic surveys under unfavorable field conditions – an application in land use and cover change studies in the Amazon

ABSTRACT We describe the use of tablet computers with ESRI Survey123 for data collection in sociodemographic surveys applied to land use and cover change studies. Based on the administration of 716 questionnaires during the expedition carried out in 2022 in 64 rural communities along the Rio Negro River, in the Brazilian Amazon, we evaluate the advantages of computer-aided personal interviewing (CAPI) instead of paper-and-pencil interviewing (PAPI). The results point to reduced research time and costs, including for training, fieldwork supervision, and data processing. The unit cost of the questionnaire was reduced by an estimated 10%. We observed positive impacts on data quality, contact with communities, and dissemination of geocoded results. We conclude that the approach adopted by us was sufficient for the success of the survey, which indicates that CAPI can be used under unfavorable field conditions (lack of electricity and poor internet connection).

What causes deforestation and land cover change in Riau Province, Indonesia

Riau has experienced massive forest conversion and the highest deforestation rate in Sumatra and the world. International and local level deforestation and land cover change studies in Riau already exist. However, understanding the drivers and actors behind this land cover change remains challenging, partly because the studies are spread across many domains and disciplines. We provide a literature review of 101 studies identifying the causes and actors of land cover change in Riau Province. Our review shows that oil palm and timber plantations are the most prominent direct causes. The lack of capacity and policy failures were the most prominent underlying causes of deforestation and land cover change. Our review also shows that companies and smallholders are the main actors in the direct causes. Central and local governments are the main actors in the underlying causes of deforestation and land cover change. Our literature review shows knowledge gaps that can be filled by classifying the causes and roles of actors in deforestation and land cover change.

Assessment of Landcover Change of Kathmandu District, Nepal

It is necessary to understand land cover changes for managing and monitoring natural resources and development, especially urban planning. Remote sensing and geographical information systems (GIS) are proven tools for assessing land use and land cover changes, which helps planners advance sustainability. Google Earth Engine is used in this study to detect land cover changes in one of the rapidly growing cities in Nepal. It was discovered that from 2013 to 2019, 0.26% of the total area was increased by forests, 3.28% by settlement, 0.015% by wetland, and 1.21% by otherland. The overall accuracy and kappa coefficient of the landcover change study for 2013 are 80% and 0.74, and the overall accuracy and kappa coefficient of the study of landcover change for 2019 are 83.33% and 0.78. The status of the landcover change in Kathmandu district before and after the earthquake showed that forest covers the highest area, followed by cropland, and then settlement in both years 2013 and 2019. Forest, settlement, wetland, and other land have increased by 0.26%, 4.54%, 0.015%, and 1.21%, respectively. However, cropland and grassland have been decreased by 3.28% and 0.22% respectively.

Study of Land Cover Change in the City with the Fastest Economic Growth in China (Hefei) from 2000 to 2020 Based on Google Earth Engine Platform

Hefei’s gross domestic product (GDP) growth rate ranks first among all cities in China, and it was the fastest-growing city in China from 2000 to 2020. The high-speed economic development inevitably led to rapid changes in land cover types, e.g., an increment in artificial features (built-up) and decrement in natural features (vegetation). However, (1) many previous studies focus on the land cover change in metropolis or at the global scale, yet few focus on underdeveloped but fast-growing cities; (2) land cover studies mainly focus on global variations, yet seldom on local characteristics. Thus, it is of great significance to monitor the land cover change for the city with the fastest economic growth in China based on the long time-series satellite images from both global and local perspectives. In this study, with support from huge amounts of data (including 719 Landsat TM/ETM+/OLI satellite images, land surface temperature, nighttime satellite images, DEM, multiple land cover products, and various auxiliary data), processing and parallel computing abilities of the GEE platform, classification maps of land cover in Hefei from 2000 to 2020 are produced based on a random forest machine learning method, and the spatio-temporal variations and driving factors are analyzed from both global and local viewpoints. The results show that: (1) the classification accuracy is excellent; the average overall accuracy is 93% and the Kappa coefficient is 0.88; (2) the general spatio-temporal variations in land cover in Hefei from 2000 to 2020 are obvious; the built-up area expanded from 419.72 km2 to 1530.20 km2, with a total growth rate of 264.58%. With the expansion of the built-up area, the vegetation coverage decreased by 16.61% (1652.56 km2); (3) the land surface temperature shows an increment trend in the new town yet a decrement trend in the old town due to the change in vegetation coverage and the decentration of administration centers; further analysis shows that the population and the social economy are two driving factors for land cover changes. It is worth noting that both the area and coverage of vegetation in the old town and water body area in Hefei increased significantly, although the fast urbanization inevitably caused a decrement in vegetation and water area in the whole city, indicating both the high-speed economic development and improvement in green surfaces simultaneously experienced in Hefei from 2000 to 2020.

Class dynamics and relationship between land-use systems and surface temperature in south-eastern Ghana

A fifty-year study of land cover changes in Ghana’s south-eastern region is conducted to identify major shifts and new avenues for justifiable growth and development. This study sought to assess the historical changes (1970–2020) associated with the region’s land use systems, topography and land surface temperature. It further investigated the relationship between some given remotely sensed variables using autocorrelation and geoinformatics. Findings proved socio-political and economic factors have caused massive shift in land cover and prevailing climatic conditions through increasing settlements and migration, the extensiveness of agriculture, poverty, unregulated and unreported logging of trees, small-scale mining intensification, and weak governance systems. We discovered that the natural vegetation had dramatically reduced (− 52.01%), whilst built-up (+ 406.05%), farmlands/shrubs (+ 86.47%), and waterbodies (+ 47.35) were faced with a drastic increase. Class contribution rates show built environment massively influenced land modification, compared to other surveyed classes. In light of the major influences observed, it can be concluded that dynamics in land-use systems caused a substantial drift in local temperature. Temperature and built-up index correlated strongly (R2 =0.959, p < .0001) , whilst depicting a negative association against vegetation (R2 =0.959, p < .0001) and water index (R2 = 0.958, p < .0001). Variance assessment proved that the linear correlation model for the understudied elements is suitable. The study provides policy guidance amid sustainability concerns on streamlining land use activities in development planning and preservation of forests and river ecosystems that protect flora and fauna to enhance biodiversity and sustainable use of land and water resources.

Effects of Land Use Changes on Ecosystem Service Value in Xiangjiang River Basin, China

The study of land use and land cover (LULC) change and the evolution of ecosystem service values (ESV) is important for optimizing the allocation of regional land resources and achieving sustainable development, but traditional land use analysis methods cannot dig deeper into the information on the internal transitions between different land types. Therefore, in this paper, we use the component analysis and Intensity Analysis methods to systematically analyze the land use landscape changes at multiple levels. In addition, the spatial and temporal dynamic characteristics of ESV in the Xiangjiang River Basin are carved with the help of equivalence factors and GIS spatial analysis methods, which reveal the response of ESV changes to land use changes in the Xiangjiang River Basin in the past four decades. Our results showed that, (1) in the past 40 years, the intensity of land use change in the Xiangjiang River Basin has been increasing, mainly in quantity and shift. The increase of built-up and bare land and the decrease of cultivated land are stable and active, and the loss of forest land is large, but it is dormant. The loss of cultivated and forested land flows mainly to built-up land. (2) In the Xiangjiang River Basin, ESV increases first and then decreases, mainly in the middle and high grades and changes faster in the east. (3) The cross-sensitivity coefficient reflected that the net conversion of cultivated land to forest land and water area had a promoting effect on ESV. Our results provide important knowledge to inform land use decisions and facilitate sustainable development in the Xiangjiang River Basin.

Деградація земних покривів Харківської області внаслідок воєнних дій

Background. The analysis of trends in land cover changes will allow to detect trends in land cover changes, which will contribute to the understanding of the reasons for changes in natural ecosystems and the development of strategies for their preservation and restoration. The analysis of land cover changes can be useful for assessing the impact of anthropogenic and natural factors on land using, which is important for making decisions about the rational using of natural resources, especially in the post-war period. The purpose of the research is to allow to detect the trends of land cover changes in Kharkiv region as a result of hostilities, using the satellite materials and statistical data from open sources. Methods. For the research, materials from remote sensing of the Earth were utilized, including methods of their processing and visualization. M a t h e m a t i c a l and statistical methods were applied to process statistical information and obtain index images resulting from the processing of satellite images and the generation of thematic raster data. The article conducts an analysis of the main trends in land cover changes in the Kharkiv region, highlighting trends for the most significantly altered land cover types, specifically forests and agricultural lands, for the period 2015-2022. Results. A general trend since 2015 has been the reduction of forested areas and agricultural lands, with a significant decrease in 2022, as a result of military actions and their consequences. Land cover degradation due to military activities is currently a prominent trend, representing the primary tendency in land cover changes. As a result of military actions in the Kharkiv region, all natural resources have suffered: lands from pollution and contamination with various types of waste, atmospheric air from emissions due to explosions and fires, water bodies, forest resources, and fauna from enemy equipment, pollution, and deliberate destruction. Conclusions. For a more detailed study of land cover changes related to military activities, especially regarding the destruction of the humus layer, soil pollution with metal fragments and explosive residues, field research and the use of high-resolution aerial or satellite imagery are necessary.

Land use/ land cover change study of the lower Tapi river basin using Remote Sensing and Geographic Information System

Land use/ land cover change study of the lower Tapi river basin using Remote Sensing and Geographic Information System

An Operational Assessment Framework for Near Real-time Cropland Dynamics: Toward Sustainable Cropland Use in Mid-Spine Belt of Beautiful China

Cropland monitoring is a crucial component for a broad user community from Land Use and Land Cover Change study to food security policy making. Faced with the rich natural ecological environment and variable agricultural production conditions of Mid-Spine Belt of Beautiful China (MSBBC), this study developed a novel operational assessment framework that combined the near real-time land cover mapping platform (i.e., FROM-GLC Plus), the FAO Agricultural Stress Index System, and the land degradation monitoring method suggested by United Nations Convention to Combat Desertification for the timely monitoring of cropland extent change, cropland conditions, and cropland degradation. With integrated monitoring system, this framework can provide convenient access to high-spatiotemporal- resolution cropland maps (30 m, dekadal) and instant (near real time) cropland dynamics. According to the monitoring results, we found that the abnormally high temperatures of summer 2022 adversely affected crop health in the southwest of MSBBC. Besides, our results suggested that China’s ecological restoration projects made remarkable achievement in MSBBC. The productivity of more than 70% of cropland in MSBBC has improved, and only ~6% cropland (~3.69 × 10 4 km 2 ) has degraded since 2000, mainly distributed in cropland with steep slope, insufficient precipitation, and intensive use. Site-specific measures, such as conservation tillage, improved tillage systems, and cropland ecological projects, should be adopted for sustainable cropland use and further increase in land carrying capacity of MSBBC to achieve balanced east-west development in China.

IRS LISS3-based study of spatio-temporal land use and land cover changes and their relationship with the Ahiran watershed of Hasdeo River in Central India

The Hasdeo River watershed is the source of various land use practices. Human activities have a long-term impact on land use/cover changes and the sustainability of a watershed to research aims to assess changes in land use/land cover (LULC) in the Ahiran subwatershed of the Hasdeo River in Central India, based on temporal analysis of independently produced classified images, Normalized Difference Vegetation Index (NDVI), and Principal Component Analysis (PCA) from 2000 to 2013. The comparison of the LULC change maps over different time periods (2000-2013) shows that the land use structures within the study region have changed. The land use intensity within the study region indicates the degree of human activities on the lands, which may be important indicators of land use pattern. During the thirteen years, the dense forest region rise is hyperbolic due to the establishment of plantations and other tree species in barren and scrublands. Expansion of mining, industrial activities, and settlements has to hydrological changes also. The NDVI and SAVI indicate of healthy and unhealthy vegetation in subwatersheds when compared to various LULC. PCA demonstrates a strong relationship between barren land and riverbed, water resources, and dense forest to conclude, subwatershed is currently due to intensive anthropogenic activities. Good government policies which encourage the growth of forests in the vicinity of mining areas through social forestry should be implemented.

Spatial Study of Land Cover Changes and Land Surface Temperature in Bekasi Regency, West Java, Indonesia

The increase in the built-up area in the Jakarta and its surrounding area influences the surrounding area so that there is the propagation of the built-up area and an increase in ground surface temperature. This study aims to analyze the pattern of land cover and land surface temperature in 2004, 2012, and 2020, identify the relationship between NDBI, NDVI, and land surface temperature, and predict land cover and land surface temperature in 2028 in Bekasi Regency. The method used is statistical analysis and prediction analysis with MLP-MC. The results are that the ground surface temperature increase occurred in Bekasi Regency from 2004 – 2020. The increase occurred in the types of built-up land cover such as settlements, industry, and roads. The biggest land cover change occurred in rice fields into settlements. From the statistical results, the mean land surface temperature, settlement land cover, industry, and roads also experienced an increase in temperature. NDBI can be positively correlated with land surface temperature, while NDVI is negatively correlated. In 2028, there will be an increase in the settlement area, which also results in a decrease in the areas of rice fields. This also has an impact on increasing the temperature of the land surface in the area that is experiencing changes.

Investigating the Relationship between Land Use/Land Cover Change and Land Surface Temperature Using Google Earth Engine; Case Study: Melbourne, Australia

The rapid alteration to land cover, combined with climate change, results in the variation of the land surface temperature (LST). This LST variation is mainly affected by the spatiotemporal changes of land cover classes, their geospatial characteristics, and spectral indices. Melbourne has been the subject of previous studies of land cover change but often over short time periods without considering the trade-offs between land use/land cover (LULC) and mean daytimes summer season LST over a more extended period. To fill this gap, this research aims to investigate the role of LULC change on mean annual daytime LST in the hot summers of 2001 and 2018 in Melbourne. To achieve the study’s aim, LULC and LST maps were generated based on the cost-effective cloud-based geospatial analysis platform Google Earth Engine (GEE). Furthermore, the geospatial and geo-statistical relationship between LULC, LST, and spectral indices of LULC, including the Normalised Difference Built-up Index (NDBI) and the Normalised Difference Vegetation Index (NDVI), were identified. The findings showed that the mean daytime LST increased by 5.1 °C from 2001 to 2018. The minimum and maximum LST values were recorded for the vegetation and the built-up area classes for 2001 and 2018. Additionally, the mean daytime LST for vegetation and the built-up area classes increased by 5.5 °C and 5.9 °C from 2001 to 2018, respectively. Furthermore, both elevation and NDVI were revealed as the most influencing factors in the LULC classification process. Considering the R2 values between LULC and LST and their NDVI values in 2018, grass (0.48), forest (0.27), and shrubs (0.21) had the highest values. In addition, urban areas (0.64), bare land (0.62), and cropland (0.61) LULC types showed the highest R2 values between LST regarding their NDBI values. This study highlights why urban planners and policymakers must understand the impacts of LULC change on LST. Appropriate policy measures can be proposed based on the findings to control Melbourne’s future development.

Assessing the Impact of Neighborhood Size on Temporal Convolutional Networks for Modeling Land Cover Change

Land cover change (LCC) studies are increasingly using deep learning (DL) modeling techniques. Past studies have leveraged temporal or spatiotemporal sequences of historical LC data to forecast changes with DL models. However, these studies do not adequately assess the association between neighborhood size and DL model capability to forecast LCCs, where neighborhood size refers to the spatial extent captured by each data sample. The objectives of this research study were to: (1) evaluate the effect of neighborhood size on the capacity of DL models to forecast LCCs, specifically Temporal Convolutional Networks (TCN) and Convolutional Neural Networks (CNN-TCN), and (2) assess the effect of auxiliary spatial variables on model capacity to forecast LCCs. First, each model type and neighborhood setting configuration was assessed using data derived from multitemporal MODIS LC for the Regional District of Bulkley-Nechako, Canada, comparing subareas exhibiting different amounts of LCCs with trends obtained for the full region. Next, outcomes were compared with three other study regions. The modeling results were evaluated with three-map comparison measures, where the real-world LC for the next timestep, the real-world LC for the previous timestep, and the forecasted LC for the next year were used to calculate correctly transitioned areas. Across all regions explored, it was observed that increasing neighborhood sizes improved the DL model’s capabilities to forecast short-term LCCs. CNN–TCN models forecasted the most correct LCCs for several regions while reducing error due to quantity when provided additional spatial variables. This study contributes to the systematic exploration of neighborhood sizes on selected spatiotemporal DL techniques for geographic applications.