Efficient large-scale land cover change detection using Google Earth Engine: Climate-driven vegetation dynamics in Asian drylands (2001–2022)

Abstract. Land cover is the physical material at the surface of the Earth. As the cause and result of global environmental change, land cover change (LCC) influences the global energy balance and biogeochemical cycles. Continuous and dynamic monitoring of global LC is urgently needed. Effective monitoring and comprehensive analysis of LCC at the global scale are rare. With the latest version of GLASS (Global Land Surface Satellite) CDRs (climate data records) from 1982 to 2015, we built the first record of 34-year-long annual dynamics of global land cover (GLASS-GLC) at 5 km resolution using the Google Earth Engine (GEE) platform. Compared to earlier global land cover (LC) products, GLASS-GLC is characterized by high consistency, more detail, and longer temporal coverage. The average overall accuracy for the 34 years each with seven classes, including cropland, forest, grassland, shrubland, tundra, barren land, and snow/ice, is 82.81 % based on 2431 test sample units. We implemented a systematic uncertainty analysis and carried out a comprehensive spatiotemporal pattern analysis. Significant changes at various scales were found, including barren land loss and cropland gain in the tropics, forest gain in the Northern Hemisphere, and grassland loss in Asia. A global quantitative analysis of human factors showed that the average human impact level in areas with significant LCC was about 25.49 %. The anthropogenic influence has a strong correlation with the noticeable vegetation gain, especially for forest. Based on GLASS-GLC, we can conduct long-term LCC analysis, improve our understanding of global environmental change, and mitigate its negative impact. GLASS-GLC will be further applied in Earth system modeling to facilitate research on global carbon and water cycling, vegetation dynamics, and climate change. The GLASS-GLC data set presented in this article is available at https://doi.org/10.1594/PANGAEA.913496 (Liu et al., 2020).

The world around us is constantly changing, and humans contribute to many of these changes. Land cover and land use (LCLU) changes over time have a significant impact on the functioning of the Earth, particularly climate change and global warming. Spatial data of LCLU changes find important applications in land management, monitoring the sustainable development of agriculture, forestry, rural areas, assessing the state of biodiversity and urban planning.In the frame of the InCoNaDa project "Enhancing the user uptake of Land Cover / Land Use information derived from the integration of Copernicus services and national databases”, the maps of land cover (LC) changes were developed for two study areas - the Łódź Voivodeship in Poland and the Viken County in Norway. The detection of LC changes was performed on the annual bases for the period 2018-2021 based on the analysis of multitemporal optical data from the Sentinel-2 mission. The Google Earth Engine (GEE) platform was used, which allows to analyze satellite data and to perform spatial analyses anywhere in the World while providing computing power. The LC change detection method was divided into two phases. The first phase is based on the analysis of spectral signatures, and the second phase applies the machine learning Random Forest algorithm. The classification was performed separately for each time interval: 2018-2019, 2019-2020, 2020-2021. In this way, three independent classification models were developed for each study area. The following three LC change classes were distinguished:  a) no-change, b) forest loss, and c) construction sites and newly built-up areas. The minimum mapping unit (MMU) was 0.2 ha. The LC change detection models reached high accuracy - in both study areas for all time intervals, the overall accuracy was equal to or greater than 0.97 and the Kappa coefficient than 0.95. The independent verification carried out based on the aerial orthophotos proved that the overall accuracy of the LC changes is pretty good for both study areas (around 0.9). The changes occurring in the construction sites and newly built-up area class reached slightly lower accuracy and has the lowest precision. The presented method showed its universality and adaptability, giving the possibility for further development. We will present the method, algorithm, results and their verification for Poland and Norway.

Intertwined impacts of urbanization and land cover change on urban climate and agriculture in Aurangabad city (MS), India using google earth engine platform

Background: Land cover change refers to changes in the surface cover of an area over time due to natural and human factors. The urbanization of Cibadak District, near the toll exit, contrasts with the rural Cikidang District, resulting in different dynamics of land surface temperature (LST) and land cover change. This study focuses on the observed temperature increase in both districts from 2013 to 2023, aiming to analyze the relationship between land cover change and LST variation. Methods: This study used a spatiotemporal analysis method, with land cover as the independent variable and LST as the dependent variable. Clustered purposive sampling was used. Land cover was validated using Google Earth imagery, while LST was validated with air temperature data from BMKG. Landsat 8 imagery was processed using the Google Earth Engine (GEE) platform to create spatiotemporal maps of land cover and LST. The relationship between the two variables was analyzed through cross-sectional spatial analysis and statistical calculations, including Spearman correlation and multiple linear regression. Findings: From 2013 to 2023, the average increase in LST in land cover was 7.76°C. The analysis showed that vegetated land cover (forest and garden) showed temperatures between 24-32°C, while bare land had temperatures between 32-36°C, with bare land exceeding 40°C in 2023. The statistical results showed a strong positive correlation between land cover changes and LST increases. The correlation coefficient between 2013-2018 was 0.8117 (R² = 0.6588), and between 2018-2023, it was 0.7925 (R² = 0.6560). Conclusions: This study revealed a significant increase in LST in both study sites from 2013 to 2023, with land cover changes playing a key role in this trend. Urban areas with less vegetation contribute to higher temperatures, while vegetated areas help mitigate temperature increases. Novelty/Originality of this article: This study uniquely combines spatiotemporal analysis and statistical methods to assess the impact of land cover change on LST dynamics.

Analysis of the spatiotemporal changes in global land cover from 2001 to 2020

Uyo City in Akwa Ibom State, Nigeria has experienced rapid urban growth and development over the past decades. The urban expansion has led to different land cover transitions which in turn have caused significant changes in key environmental parameters such as Land Surface Temperature (LST) and Normalised Difference Vegetation Index (NDVI). This study investigated land cover changes in Uyo and the relationship with LST and NDVI. Landsat multispectral imageries covering the study area were acquired for three periods – 1986, 2000 and 2018. Land cover was extracted using the Maximum Likelihood Classification (MLC) technique, LST was derived using a single channel algorithm applied on the imagery thermal bands, and the NDVI equation was applied to the imageries. To assess the MLC accuracy, four different accuracy metrics were calculated – user's accuracy, producer's accuracy, overall accuracy, and kappa coefficient. Change statistics were computed to evaluate the transition dynamics of each land cover class. Finally, the relationship between land cover, LST and NDVI was evaluated using the Contribution Index (CI) and Pearson's Correlation analysis. Between 1986 and 2018, vegetation declined from 278 km2 to 219 km2, wetlands declined from 20 km2 to 17 km2, barren land declined from 33km2 to 25km2 while built-up areas increased from 69 km2 to 139 km2. There were significant transitions in land cover for instance, 78km2 of vegetation and 14km2 of barren land were converted to built-up area over the 32 years. The mean LSTs in the city were 21.67 °C (1986), 25.40 °C (2000) and 26.04 °C (2018). The highest contribution to LST was from built-up areas while the lowest was from vegetation. The CI of built-up areas rose from 0.08 in 1986 to 0.30 in 2018, Similarly, LST profiles showed that the diffusion of higher LSTs across the study area was in tandem with the horizontal expansion of built-up areas. There was also a high negative correlation between LST and NDVI at the three periods of study. It is recommended that the Uyo local authorities take deliberate measures and policies aimed at moderating urban growth while ensuring the conservation of urban greens spaces in the city.

Unprecedented human-induced land cover changes happened in China after the Reform and Opening-up in 1978, matching with the era of Landsat satellite series. However, it is still unknown whether Landsat data can effectively support retrospective analysis of land cover changes in China over the past four decades. Here, for the first time, we conduct a systematic investigation on the availability of Landsat data in China, targeting its application for retrospective and continuous monitoring of land cover changes. The latter is significant to assess impact of land cover changes, and consequences of past land policy and management interventions. The total and valid observations (excluding clouds, cloud shadows, and terrain shadows) from Landsat 5/7/8 from 1984 to 2017 were quantified at pixel scale, based on the cloud computing platform Google Earth Engine (GEE). The results show higher intensity of Landsat observation in the northern part of China as compared to the southern part. The study provides an overall picture of Landsat observations suitable for satellite-based annual land cover monitoring over the entire country. We uncover that two sub-regions of China (i.e., Northeast China-Inner Mongolia-Northwest China, and North China Plain) have sufficient valid observations for retrospective analysis of land cover over 30 years (1987–2017) at an annual interval; whereas the Middle-Lower Yangtze Plain (MLYP) and Xinjiang (XJ) have sufficient observations for annual analyses for the periods 1989–2017 and 2004–2017, respectively. Retrospective analysis of land cover is possible only at a two-year time interval in South China (SC) for the years 1988–2017, Xinjiang (XJ) for the period 1992–2003, and the Tibetan Plateau (TP) during 2004–2017. For the latter geographic regions, land cover dynamics can be analyzed only at a three-year interval prior to 2004. Our retrospective analysis suggest that Landsat-based analysis of land cover dynamics at an annual interval for the whole country is not feasible; instead, national monitoring at two- or three-year intervals could be achievable. This study provides a preliminary assessment of data availability, targeting future continuous land cover monitoring in China; and the code is released to the public to facilitate similar data inventory in other regions of the world.

Annaba, Algeria's fourth largest city, has acquired national and international importance due to its openness to the Mediterranean Sea. Over the last ten years, its rapid sprawl has continued to exacerbate the situation, leading to increased consumption of space, particularly green structures. The main objective of this study is to assess changes in land use and land cover (LULC) over the last 30 years, focusing on the green structure of the future metropolis.
 Google Earth Engine (GEE) was used to explore land cover classification using the random forest algorithm. A spatial model of the main changes in land cover between 1984, 2004 and 2021 was also generated.
 The principal drivers of land use change are human activities and urbanization, including fires and land clearing.The spatial pattern of change is mainly due to inappropriate investment policy and uncontrolled urbanisation. This is explained by the main results of the land use conversion processes between 1984 and 2021. The comparison shows a decline in forests and green land, mainly due to conversion to urbanised land, cropland, bare land or other land. Similarly, bare land and other types of land declined over the 1984-2004 period in favour of urbanised or cultivated land. Furthermore, it compromises any possibility of sustainable development at a time when we are facing climate change.

China has experienced intense land use and land cover changes during the past several decades, which have exerted significant influences on climate change. Previous studies exploring related climatic effects have focused mainly on one or two specific land use changes, or have considered all land use and land cover change types together without distinguishing their individual impacts, and few have examined the physical processes of the mechanism through which land use changes affect surface temperature. However, in this study, we considered satellite-derived data of multiple land cover changes and transitions in China. The objective was to obtain observational evidence of the climatic effects of land cover transitions in China by exploring how they affect surface temperature and to what degree they influence it through the modification of biophysical processes, with an emphasis on changes in surface albedo and evapotranspiration (ET). To achieve this goal, we quantified the changes in albedo, ET, and surface temperature in the transition areas, examined their correlations with temperature change, and calculated the contributions of different land use transitions to surface temperature change via changes in albedo and ET. Results suggested that land cover transitions from cropland to urban land increased land surface temperature (LST) during both daytime and nighttime by 0.18 and 0.01 K, respectively. Conversely, the transition of forest to cropland tended to decrease surface temperature by 0.53 K during the day and by 0.07 K at night, mainly through changes in surface albedo. Decreases in both daytime and nighttime LST were observed over regions of grassland to forest transition, corresponding to average values of 0.44 and 0.20 K, respectively, predominantly controlled by changes in ET. These results highlight the necessity to consider the individual climatic effects of different land cover transitions or conversions in climate research studies. This short-term analysis of land cover transitions in China means our estimates should represent local temperature effects. Changes in ET and albedo explained <60% of the variation in LST change caused by land cover transitions; thus, additional factors that affect surface climate need consideration in future studies.

The land cover of Bohai Rim region has changed greatly due to urbanization and economic development. Monitoring the land cover with high accuracy and real time is the most important basis for relevant researches. Traditional single-machine processing mode is difficult to realize rapid monitoring for large-scale and long-time series. The emergence of remote sensing big data makes it possible to combine computing platform and massive data. The land cover maps of study area were interpreted based on Google Earth Engine (GEE) platform with decision tree (CART) method from 2000 to 2019. The land cover change was analyzed, and the interpretation results using different data sources were compared. The results showed that the GEE platform could realize the rapid land cover interpretation in a large area, which interpreted coastal wetlands and other cover types with high accuracy over 80% comparing the surveyed points. Compared with Landsat images, the Sentinel-2A images interpretation results had a great improvement in accuracy, which increased from 85% to 95%, and thus more detailed surface information could be reflected. In 2000, the area of wetland, build-up area, farmland, forest, and water in the study area were 1612.5, 5734.9, 32074.8, 11853 and 3504.3 km2, accounting for 2.9%, 10.5%, 58.6%, 21.6% and 6.4% respectively. By 2019, wetlands had been reduced by 775.1 km2, with a decline of 40.1%; built-up area increased by 5310.5 km2 with an increasing rate of 92.6%. The area of farmland, forestland and water area decreased 1841.6, 1823.5 and 870.3 km2, with a decreasing rate of 5.7%, 24.8% and 48.1%, respectively. The coastal urbanization process caused the occupation of built-up area to other land use types, which was the main driving force of land cover change in the study area.

Introduction Although numerous land cover datasets can act as references for understanding land cover change in China, the inconsistencies between the datasets can also provide understanding. Previous studies on the consistency between land cover datasets have mostly focused on land cover type consistencies and have ignored data consistencies in land cover change. Outcomes Therefore, we aim to analyse the consistencies in land cover changes through likelihood assessment methods. We compared the spatiotemporal changes in forest, grassland, cropland, and bare land in the Climate Change Initiative land cover dataset (CCI-LC), Moderate-resolution Resolution Imaging Spectroradiometer land cover dataset (MCD12Q1), China’s National Land Use and Cover Change (CNLUCC), Globeland30 and Global Land Cover Fine Surface Covering 30 (GLC-FCS30) datasets in 2010. The results showed that the percentages and changes in each land cover type in MCD12Q1 were different from those in the other datasets. Discussion For example, the proportion of grassland in MCD12Q1 was the highest, reaching 48.04%. The places with high consistency were the places where the land cover types were concentrated, and the bare land had the highest consistency. However, the consistency of China’s land cover change was quite low, and the percentage of low consistency was more than 87% from 2000-2018. Comparison of the data with the global artificial impervious area (GAIA) and Hansen-Global Forest Change (Hansen-GFC) datasets showed that the percentage of high construction gain consistency (38.83%) was higher than the forest change consistency, and the percentage forest loss high consistency (8.85%) was lower than the forest gain high consistency (12.76%). Conclusion The results not only provide a basis for the use of land cover datasets but also give a clearer understanding of the pattern of land cover changes.

Population growth, urbanization, policy changes, economic activities, agriculture, infrastructure development, and climate change are some of the factors that can lead to land cover changes. This necessitates serious monitoring to determine the extent of land changes occurring. Semarang City is one of the cities that has undergone significant land changes. This can be seen from the substantial areas that have undergone land-use conversion. This study aims to observe land cover changes in Semarang City using Landsat 8 TOA satellite imagery analyzed through the Google Earth Engine (GEE) platform. GEE is an alternative for image processing as it simplifies the process of image analysis compared to conventional desktop-based image processing methods. The classification is performed using a machine learning algorithm with the Classification and Regression Trees (CART) method tha available in GEE. The accuracy of the classification is tested using the confusion matrix calculation. The results obtained show the accuracy of land cover change testing for the years 2013, 2016, 2019, and 2022, with kappa accuracies reaching 96.7%, 93.78%, 94.54%, and 96.04%, respectively. The effectiveness of image processing on the GEE platform shows that GEE can be used as a fast and efficient alternative for image processing. Based on the research findings, it is shown that residential areas experience significant increases every year. Therefore, the increase in residential areas has a significant impact on the surrounding environment, such as increasing urban temperatures, which reduces the comfort level of residents, especially in Semarang City. Keywords : Land Cover, Landsat 8 Satellite Imagery, Google Earth Engine ABSTRAK Pertumbuhan populasi, urbanisasi, perubahan kebijakan, aktivitas ekonomi, pertanian, pengembangan infrastruktur, dan perubahan iklim adalah beberapa faktor yang dapat menyebabkan perubahan tutupan lahan. Hal ini memerlukan pemantauan yang serius untuk melihat seberapa besar perubahan lahan yang terjadi. Kota Semarang merupakan salah satu kota yang telah banyak mengalami perubahan lahan. Hal ini dapat dilihat dari banyaknya wilayah yang telah beralih fungsi lahan. Penelitian ini bertujuan untuk melihat perubahan tutupan lahan di Kota Semarang dengan menggunakan data citra satelit Landsat 8 TOA yang di analisis menggunakan platform Google Earth Engine (GEE). GEE menjadi alternatif pengolahan citra karena memudahkan pengguna dalam melakukan pengolahan dan analisis citra dibandingkan dengan metode konvensional pengolahan citra berbasis desktop. Klasifikasi dilakukan dengan algoritma machine learning menggunakan metode Classification and Regression Trees (CART) yang tersedia di GEE. Uji akurasi klasifikasi dilakukan dengan menggunakan perhitungan confusion matrix. Hasilnya diperoleh uji akurasi perubahan tutupan lahan pada tahun 2013, 2016, 2019 dan 2022, akurasi kappa masing-masing mencapai 96,7%, 93,78%, 94,54%, dan 96,04%. Efektifitas pengolahan citra di platform GEE menunjukkan bahwa GEE dapat digunakan sebagai alternatif dalam pengolahan citra yang cepat dan efisien. Berdasarkan hasil penelitian menunjukkan bahwa wilayah pemukiman mengalami kenaikan yang signifikan setiap tahun Oleh karena itu, peningkatan pemukiman memberi dampak yang signifikan terhadap lingkungan sekitar, seperti peningkatan suhu kota, yang menyebabkan tingkat kenyamanan penduduk semakin berkurang, terutama di Kota Semarang. Keywords : Tutupan Lahan, Citra Satelit Landsat 8, Google Earth Engine.

It is critical to consider all aspects of conservation areas, inside and outside, when maintaining them. Land cover dynamics in conservation areas mostly have not yet been considered in conservation area management practices, both geographically and temporally. The advancement of technology with cloud computing can speed up and simplify the acquisition of data and information on the dynamics of land cover changes. This study aimed to analyze the dynamics of land cover change in the Gunung Merbabu National Park (GMbNP) area from 1995 to the present. The method for determining land cover change dynamics was used and assessed by creating a code for land cover classification using the random forest classification algorithm on the Google Earth Engine (GEE) platform. The results showed that from 1995 to 2020, pine forests in GMbNP area decreased by 575.765 ha from the previous 1427,961 ha in 1995. The dynamics of land cover changes outside the area need to be the concern of area managers because agricultural land and built-up land are increasing of 5.42% and 113.2%, significantly beyond the area. Referring to those dynamic conditions, it should be a concern in planning and policy-making conservation management.

Comprehensive analysis of land use and cover dynamics in djibouti using machine learning technique: A multi-temporal assessment from 1990 to 2023

Mapping major land cover dynamics in Beijing using all Landsat images in Google Earth Engine