Nighttime Light Data Research Articles

The allometric relationship between carbon emission and economic development in Yangtze River Delta: fusion of multi-source remote sensing nighttime light data.

Exploring the allometric relationship between carbon emission and economic development can provide guidance for policy-makers who hope to accelerate carbon emission reduction and achieve high-quality development. First, based on the established DMSP/OLS and NPP/VIIRS nighttime light datasets, this study simulated the carbon emissions of the Yangtze River Delta from 2000 to 2020. Second, our research analyzed the spatiotemporal evolution characteristics of carbon emissions. Third, adopting allometric growth model, we explored the allometric relationship between economic development and carbon emissions in Yangtze River Delta. The main conclusions are as follows. First, four prediction models, namely, linear fitting, support vector machine, random forest, and CNN-BiLSTM deep learning, were compared to simulate the accuracy of carbon emissions. Consequently, the CNN-BiLSTM deep learning estimation model presented the best accuracy. Second, both the carbon emissions in YRD as a whole showed an increasing trend, with the largest growth rate appearing in Shanghai and the smallest growth rate occurring in Lishui. Moreover, the high-carbon emission areas were mainly distributed in the core city cluster, which are enclosed by Shanghai, Nanjing, and Hangzhou. Finally, the allometric relationship between economic development and carbon emissions was dominated by one-level negative during the sample period, and the relative growth rate of carbon emissions is lower than that of the economic development, which made the YRD at a basic coordinate stage of weak expansion of economy.

Production–Living–Ecological Spatial Function Identification and Pattern Analysis Based on Multi-Source Geographic Data and Machine Learning

Land use cannot be simply understood as land cover. The same land may carry different functions, such as production, living, and ecological applications; the dominant function of land will affect and restrict other uses. Disorderly urbanization and industrialization have led to an intensification of conflicts among the production, living, and ecological functions of land, which is a major constraint on regional sustainable development. This paper took the perspective of land-use function and used multi-source data such as Sentinel remote-sensing imagery, VIIRS night-time light data, and POIs to classify land-use functions on a large scale in the Beijing–Tianjin–Hebei (BTH) urban agglomeration. The specific research process was as follows. Firstly, the BTH region was multi-scale-segmented based on Sentinel remote-sensing data. Then, the spectral, texture, shape, and socio-economic features of each small area after segmentation were extracted. Moreover, a PLES land-use classification system oriented towards land-use function was established, and a series of representative samples were selected. Subsequently, a random forest model was trained using these samples; then, the trained model was used for the large-scale analysis of land use in the entire BTH region. Finally, the spatial distribution patterns and temporal–spatial evolution characteristics of PLES in the BTH region from 2016 to 2021 were analyzed from the macro level to the micro level.

Tracking electricity losses and their perceived causes using nighttime light and social media

Urban environments are intricate systems where the breakdown of critical infrastructure can impact both the economic and social well-being of communities. Electricity systems hold particular significance, as they are essential for othe infrastructure, and disruptions can trigger widespread consequences. Typically, assessing electricity availability requires ground-level data, a challenge in conflict zones and regions with limited access. This study shows how satellite imagery, social media, and information extraction can monitor blackouts and their perceived causes. Nighttime light data (in March 2019 for Caracas, Venezuela) are used to indicate blackout regions. Twitter data are used to determine sentiment and topic trends, while statistical analysis and topic modeling delved into public perceptions regarding blackout causes. The findings show an inverse relationship between nighttime light intensity and Twitter activity. Tweets mentioning the Venezuelan President displayed heightened negativity and a greater prevalence of blame-related terms, suggesting a perception of government accountability for the outages.

Satellite Monitoring of the Urban Expansion in the Pearl River–Xijiang Economic Belt and the Progress towards SDG11.3.1

Quantitative analysis of the spatiotemporal pattern of urban expansion and forecasting of the progress towards SDG11.3.1 are of great significance for the promotion of sustainable urban development. This study employed the spatiotemporal normalized threshold method to extract urban built-up areas in the Pearl River–Xijiang Economic Belt based on night-time light data and investigated the intricate patterns of urban expansion from 2000 to 2020. Then, the historical trends of the SDG11.3.1 indicators within the economic belt were evaluated, and future urban built-up areas were predicted based on the SSP1 scenario. The results indicate the following: (1) Built-up area extraction has an overall accuracy that exceeds 97% and G-mean values that all surpass 82%, indicating the high accuracy of the method. (2) The Pearl River–Xijiang Economic Belt demonstrates evident urban expansion trends, albeit with uneven development. The urban area of the economic belt has expanded from 1020.29 km2 to 3826.87 km2, the expansion direction of each city is different, and the center of gravity of the economic belt has moved to the southeast. (3) During the period from 2008 to 2020, the entire economic belt experienced a situation where the urban expansion rate was lower than the population growth rate, and there was an imbalance in urban development (LCRPGR = 0.33). However, looking ahead to the period from 2020 to 2030, the average LCRPGR for the entire economic belt shows a significant upward trend, approaching the ideal state of sustainable development (LCRPGR ≈ 1).

The first baleen whale marine protected area proposed for Bryde's whales in the Beibu Gulf, China

AbstractThe establishment of marine protected areas (MPAs) for cetaceans is an important strategy to mitigate human disturbance and protect biodiversity. Despite abundant cetacean species, there are only a few MPAs dedicated to cetacean conservation in China, all of which are for inshore dolphins. Bryde's whales, the only nearshore baleen whale population in mainland China, are conflicting with intensive human activities, yet an effective conservation strategy is lacking. This study used species distribution models to analyze distribution patterns and suitable habitats of Bryde's whales in the Beibu Gulf and proposes the first baleen whale MPA in China. Our results showed Bryde's whales have a seasonal distribution pattern in the Beibu Gulf, and that the waters around Weizhou Island and the southeastern coast of Vietnam were their core habitats. The seasonal nighttime light data indicated a negative relationship between the number of ship lights and Bryde's whale sightings and suggest that Bryde's whales might be threatened by fisheries. We proposed an MPA based on the results, suggesting that the waters within 20 km around Weizhou Island should be declared a protected area. Furthermore, we recommend that anthropogenic activities in the waters around Weizhou Island are better managed to reduce negative impacts on marine life.

Spatial-Temporal analysis of urban environmental variables using building height features

The 11th Sustainable Development Goal (SDG) is focused on sustainable cities and communities and is closely related to other SDGs such as Good health and well-being (the third SDG) and climate action (the 13th SDG). However, the lack of data has made it difficult to evaluate the success of reaching these goals. To address this, a method is proposed in this paper to generate temporal building height maps and extract features from the 3D structure of urban areas to examine their relationship with environmental variables, acquired from remote sensing satellites. Therefore, no survey data is required from the study area. Building height map is generated by processing Sentinel-1, Sentinel-2, and Nighttime light data by a UNet-based deep model. The results showed significant improvements in Mean Square Errors compared to available building maps in Berlin and London. In the second step, several features were extracted from the 3D structure of urban areas, and their relationship with environmental variables such as atmosphere contents from Sentinel-5 data and Urban Heat Island (UHI) from MODIS was examined via shallow regression models. The spatial study shows high correlation between each environmental variable and height map features in a neighborhood, with R2 scores of 0.78, 0.94, 0.92, 0.7, and 0.88 for CO2, CO, NO2, SO2, and UHI, respectively. It is found the environmental parameters are shaped by the collective building heights within a specific neighborhood, rather than hinging on the individual building heights at the sampling site. Furthermore, spatial resolution plays a significant role. In the case of the MODIS-based heat island map, a 3 km neighborhood yields a high R2-score, whereas when utilizing Sentinel-5 data, it is advisable to employ a larger neighborhood. Furthermore, the temporal study shows even higher R2 scores than the spatial domain, indicating the temporal reliability of the proposed method. The findings of this study can be used by governors and decision makers for sustainable urban development.

Outdoor light at night and depressive symptoms in male veterans: a multicenter cross-sectional study in China

ABSTRACT Previous studies have indicated depression was associated with environmental exposures, but evidence is limited for the association between outdoor light at night (LAN) and depression. This study aims to examine the association between long-term outdoor LAN exposure and depressive symptoms using data from the Chinese Veteran Clinical Research platform. A total of 6445 male veterans were selected from 277 veteran communities in 18 cities of China during 2009‒2011. Depressive symptoms were evaluated using the Chinese version of the Center for Epidemiological Studies Depression scale. Outdoor LAN was estimated using the Global Radiance Calibrated Nighttime Lights data. The odds ratio and 95% confidence intervals of depressive symptoms at the high level of outdoor LAN exposure against the low level during the 1 years before the investigation was 1.49 (1.15, 1.92) with p-value for trend < 0.01, and those associated with per interquartile range increase in LAN exposure was 1.22 (1.06, 1.40).

Decoupling economic growth from building embodied carbon emissions in China: A nighttime light data-based innovation approach

The contribution of the construction sector is indispensable for the realization of China's carbon peaking and carbon neutrality goals. However, existing studies have focused on the decoupling relationship between GDP and building life cycle carbon emissions, neglecting the utilization of Night Time Light data (NTL). The research question of this research is how to describe the decoupling relationship between Economic Growth (EG) and Building Embodied Carbon emissions (BECs) by introducing NTL. To tackle this question, the carbon emission coefficient approach is used to calculate BECs first. Then, both GDP and NTL are selected to reflect EG. The Tapio model is utilized to examine the regional and temporal evolution of China's inter-provincial decoupling performance. The main findings are as follows: 1) the number of provinces that achieved decoupling status in China is increasing, and progress has been made in BECs reduction. 2) There are significant regional differences in the decoupling of China's BECs. Particularly, most of the provinces in the south of the Hu Huanyong line show a negative decoupling for the year 2020 due to the impact of COVID-19. 3) The long-term decoupling results of GDP and NTL are consistent, while the short-term decoupling results obtained via NTL are more accurate. The study can enrich the application of NTL in the field of BECs, and provide a basis for the Government to set effective carbon reduction targets and pathways.

Optimal parameters of random forest for land cover classification with suitable data type and dataset on Google Earth Engine

Exact land cover (LC) map is essential information for understanding the development of human societies and studying the impacts of climate and environmental change. To fulfill this requirement, an optimal parameter of Random Forest (RF) for LC classification with suitable data type and dataset on Google Earth Engine (GEE) was investigated. The research objectives were 1) to examine optimum parameters of RF for LC classification at local scale 2) to classify LC data and assess accuracy in model area (Hefei City), 3) to identify a suitable data type and dataset for LC classification and 4) to validate optimum parameters of RF for LC classification with a suitable data type and dataset in test area (Nanjing City). This study suggests that the suitable data types for LC classification were Sentinel-2 data with auxiliary data. Meanwhile, the suitable dataset for LC classification was monthly and seasonal medians of Sentinel-2, elevation, and nighttime light data. The appropriate values of the number of trees, the variable per split, and the bag fraction for RF were 800, 22, and 0.9, respectively. The overall accuracy (OA) and Kappa index of LC in model area (Hefei City) with suitable dataset was 93.17% and 0.9102. In the meantime, the OA and Kappa index of LC in test area (Nanjing City) was 92.38% and 0.8914. Thus, the developed research methodology can be applied to update LC map where LC changes quickly occur.

From the coast to the interior: global economic evolution patterns and mechanisms

It is well established that nighttime light brightness value, which is measured from satellites, correlates with economic prosperity across the globe. Researchers have diverged over whether economic factors cluster in coastal areas or move to interior areas. By using nighttime light data and applying the random forest algorithm to measure the proportion of global “near regions” GDP, it was seen that global GDP decreased from 67.25% in 2000 to 63.02% in 2018. This research reveals that under the continuous promotion of economic globalization, there is still a spatial imbalance of economic development between global “near regions” and “far regions”; however, economic factors are gradually shifting to interior areas and forming a “coastal remoteness” evolution pattern. Within the intercontinental range, there are obvious differences in the evolution patterns and spatial structure of economic development between the sub-regions. The reduction of overseas transportation costs and diseconomies of scale are the primary reasons for the evolution of “coastal remoteness” in global economic development. Our findings can facilitate future policymaking and the management of global coastal and interior areas, as well as establish new horizons for relevant research topics within the context of land and marine-coordinated development.

Does cropland threaten urban land use efficiency in the peri-urban area? Evidence from metropolitan areas in China

In recent decades, cropland policies have been recognized as crucial tools for ensuring food security and managing urban growth. However, whether cropland conservation undermines urban land use efficiency (ULUE) in peri-urban areas has not been adequately studied. This study investigated the impact of cropland on ULUE in the peri-urban areas of 36 rapidly urbanizing metropolitan areas in China. Multiple open-source datasets were used, including land use, land cover, three-dimensional building structure, and nighttime light (NTL) data. Urban construction land patterns (infilling, edge, outlying) were categorized to examine the intermediate role of urban form in the correlation between cropland and ULUE. The findings indicated that: (1) high proportion of cropland area within the peri-urban areas significantly undermined ULUE; (2) although the conservation of cropland is conducive to compact urban growth, the infilling expansion pattern that compelled by cropland conservation would not sustain intensive human activity; and (3) reducing the spatial separation between conserved cropland and urban construction land was conducive to the dual objectives of protecting cropland and promoting ULUE. This study contributed to the development of a nuanced understanding of cropland protection policies that balance national food security and urbanization efficiency.

Impact of Population Density on Spatial Differences in the Economic Growth of Urban Agglomerations: The Case of Guanzhong Plain Urban Agglomeration, China

In the new period of ups and downs in the international environment, it is necessary to seek a new endogenous impetus for the economic growth of urban agglomerations. Population agglomeration provides a new idea to explain the spatial differences in the economic growth of urban agglomerations. Thus, we ask the question, does population agglomeration affect the spatial differences in the economic growth of urban agglomerations, and how? This study first measured the spatial differences in district- and county-scale economic growth in China’s Guanzhong Plain urban agglomeration from 2005 to 2020 and then constructed an empirical formula to calculate the impact of population density on the urban agglomeration’s economic growth, taking into account the roles of both intra- and inter-district and county interactions. Thus, based on the population density data extracted from nighttime lighting data, we analyzed the impact of population density on economic growth within urban agglomerations, as well as the extent of the impact of population density on economic growth when incorporating spillover effects from neighboring districts and counties. The results indicate that, firstly, the Guanzhong Plain urban agglomeration in China has formed a “core-periphery” development pattern, with the main urban areas of Xi’an–Xianyang and Baoji as the core and the core area gradually spreading out to the neighboring districts and counties of their cities. Secondly, population density can significantly and steadily promote the economic growth of the districts and counties within the urban agglomeration, and the population agglomeration of districts and counties with railway stations can have a stronger effect on the economic growth of these districts and counties. Third, the agglomeration of economic and demographic factors in neighboring counties has a positive spillover effect on the local economy, while the positive impact of population density on economic growth remains unchanged when it is integrated into the spillover effect of neighboring counties. This study not only provides a theoretical basis for systematically exploring the influence of population density on the economic growth of urban agglomerations but also provides a reference for local governments to formulate policies related to regional economic development and spatial territorial planning. According to the research conclusion, this study suggests that local governments can continue to promote the regional development policy of spatial agglomeration and intensive land planning, strengthen the construction of the industrial chain and road network within the urban agglomeration, and deepen the network connection between districts and counties.

The Influence of Traditional Ethnic Villages on Forest Structure Based on PLS-SEM: A Case Study of Miao Inhabited Area

The activity characteristics of the village and its symbiotic relationship with the environment play an important role in the sustainable development of the surrounding environment. Miao villages have a long history. In the process of long-term interaction with the surrounding natural environment, Miao villages have formed a unique forest culture, which has an important impact on the distribution of the surrounding forests and plays a crucial role in local forest management. In this study, we took the Miao villages of China that are distributed in Qiandongnan Miao and Dong Autonomous Prefecture of China as an example and constructed a research framework to study the interaction between the natural environment and human activities around the Miao villages and its impact on forest change based on partial least squares structural equation modeling (PLS-SEM) and geographically weighted regression modeling (GWR) methods. The validity and reliability evaluations showed that the PLS-SEM model was reasonable. The results showed that the Miao villages were randomly distributed within 0–2 km and clustered in the 8–10 km buffer zone. The temporal variation of the forest landscape around the Miao villages was small, and the spatial heterogeneity was obvious. Within the 0~2 km buffer zone, the proportion of closed-canopy forest was the largest, and with the increase in the buffer zone radius, the proportion of closed-canopy forest gradually decreased, the open-canopy forest gradually grew, and the proportion of shrubbery and other forests showed an upward trend first and then a downward trend. Temporally, the four forest landscapes did not change much, with closed and open forests sliding, and shrubbery and other forests increasing. Regarding the drivers of forest structure change, topographic factors and landscape patterns had a positive effect on forest structure, while human activities had a negative effect. The influence of topography on human activities in the Miao villages weakened the direct positive effect of topography on forests and promoted the positive effect of the landscape pattern on forests. There were significant spatial differences in the GWR regression coefficients of the effects of different factors on forest structure in 2020, with a pivotal negative correlation between NDVI and night-time light data. In addition, the higher the elevation, the more unfavorable the distribution of open-canopy forests and the better the distribution of closed-canopy forests. The higher the slope, the higher the NDVI but the more unfavorable the distribution of closed-canopy forests. In general, the impacts of Miao villages on forest structure are highly complex and interactive, with both direct and indirect effects. Different factors interact to affect the structure of the forest. The study on the effect of Miao villages on forests is helpful for more targeted forest protection and the formulation of laws and regulations, so as to find a balance between human activities and forest management, in order to maintain the ecological balance of local areas. This study introduced the PLS-SEM model to investigate the impacts of Miao villages on forest structure, which effectively enhanced our understanding of the drivers and impacts of forest change and provides theoretical support and a basis for forest protection and management.

Using Dual Spatial Clustering Models for Urban Fringe Areas Extraction Based on Night-time Light Data: Comparison of NPP/VIIRS, Luojia 1-01, and NASA’s Black Marble

Night-time light data (NTL) have been extensively utilized to map urban fringe areas, but to date, there has not been a comprehensive evaluation of the existing spatial clustering methods for delineating the urban fringe using different types of night-time light data. Therefore, we first selected three popular sources of night-time light data (i.e., NPP/VIIRS, Luojia 1-01, and NASA’s Black Marble) to identify the urban fringe. The recognition of spatial mutations across the urban–rural gradient was conducted based on changes in night light intensity using a spatial continuous wavelet transform model. Then, we employed three representative dual spatial clustering approaches (i.e., MK-Means, DBSC, and DSC) for extracting urban fringe areas using different NTL. By using dual spatial clustering, the spatial patterns of the mutation points were effectively transformed into homogeneous spatially adjacent clusters, enabling the measurement of similarity between mutation points. Taking Nanjing city, one of China’s megacities, as the study area, we found that (1) Compared with the fragmented and concentrated results obtained from the Luojia 1-01, NASA’s Black Marble and NPP/VIIRS data can effectively capture the abrupt change of urban fringes with NTL variations; (2) DSC provided a reliable approach for accurately extracting urban fringe areas using NASA’s Black Marble data.

Spatio-temporal variations of aerosol optical depth over Ukraine under the Russia-Ukraine war

The ongoing Russia-Ukraine war has an impact on air quality in the contested region, but it is difficult to assess it during the war and to distinguish between weather conditions and anthropogenic impacts on air pollution. Aerosol optical depth (AOD) might be a way to indicate the regional air quality remotely. In this study, we analyze satellite-based MODIS Multi-Angle Implementation of Atmospheric Correction (MAIAC) AOD products to compare monthly mean AOD values before and during the war. By examining the spatial-temporal distribution of AOD in 2022 and comparing it with a baseline period from 2012 to 2021, we aim to assess the impact of the conflict. Our analysis employs a time series algorithm that decomposes long-term trends and seasonal variations, enabling us to identify AOD changes associated with the war-induced artificial perturbations. Additionally, we utilize satellite-based tropospheric NO2 data and nighttime lighting data as auxiliary sources to support the analysis of abnormal AOD changes resulting from the war. Furthermore, four parameters from Aerosol Robotic Network (AERONET) measurements in the Kyiv site, including angstrom exponent (AE), single scattering albedo (SSA), refractive index (RI), fine mode fraction (FMF) were exclusively discussed to explore the possible changes of aerosol physical-optical properties over Ukraine during the war. Results showed that air quality in Ukraine has been affected by the war in contradictory ways at different levels. At the national level, atmospheric pollution has dropped across Ukraine due to a decrease in the sources of air pollution emissions as a result of the suppression of economic and agricultural activities. Meanwhile, atmospheric air quality has deteriorated at the local scale where war is intense due to the large amounts of air pollutants emitted by explosions. Specifically, a significant decrease in AOD of 22.46% compared to the baseline period was observed across Ukraine in January and February 2022 before the war. Additionally, there was a column density reduction of over 10% for tropospheric NO2 compared to the same period in the previous year. Following the outbreak of the war on February 24, significant increases in AOD were observed in March when compared to the baseline period. Eastern Ukraine experienced a significant increase of 40.14%, while northern Ukraine and central Ukraine saw rises of 34.15% and 45.78%, respectively. In April, a wider distribution of areas with significantly high AOD values across Ukraine was observed compared to March. In July, widespread areas with anomalous low AOD appeared in northern and western Ukraine, likely due to a decrease in post-harvest agricultural burning caused by the war. In August, anomalous high AOD areas were observed in central Ukraine, possibly attributed to continued Russian long-range strikes and a new round of bombardments.

Nighttime lights data and their implications for IB research

Nighttime lights data and their implications for IB research

Mapping urban living standards and economic activity in developing countries with energy data.

Urban data deficits in developing countries impede evidence-based planning and policy. Could energy data be used to overcome this challenge by serving as a local proxy for living standards or economic activity in large urban areas? To answer this question, we examine the potential of georeferenced residential electricity meter data and night-time lights (NTL) data in the megacity of Karachi, Pakistan. First, we use nationally representative survey data to establish a strong association between electricity consumption and household living standards. Second, we compare gridded radiance values from NTL data with a unique dataset containing georeferenced median monthly electricity consumption values for over 2 million individual households in the city. Finally, we develop a model to explain intra-urban variation in radiance values using proxy measures of economic activity from Open Street Map. Overall, we find that NTL data are a poor proxy for living standards but do capture spatial variation in population density and economic activity. By contrast, electricity data are an excellent proxy for living standards and could be used more widely to inform policy and support poverty research in cities in low- and middle-income countries.

Did it increase energy consumption? A difference-in-differences evaluation of a rural electrification policy in Gujarat, India using night-time lights data

Electricity access is an important issue and building capacity for it requires drawing relevant lessons from past policies. In this study, we evaluate the effect of the Jyotigram Yojana, or the lighted village scheme, a supply-side policy intervention during 2003–08 to increase rural electricity access in Gujarat, India. We hypothesize that policy implementation is associated with increased electricity consumption. To test this hypothesis, we exploit variation in the timing of policy implementation at the village level, and use a generalized difference-in-differences strategy for identification. Further, we use night-time luminosity measured through remote sensing as a proxy for electricity consumption, and control for weather, village fixed effect, year fixed effect, and village or administrative block specific time trend. We find that while the overall effect of the policy on night-time luminosity was not statistically significant, the effects were likely heterogeneous, with the night-time luminosity increasing in some districts after policy implementation and decreasing in others. We conclude that the policy might have had a re-distributive effect on electricity access or consumption and recommend adopting a more holistic approach – incorporating both supply-side and demand-side measures – to increase electricity access.

Enhanced urban growth modelling: Incorporating regional development heterogeneity and noise reduction in a cellular automata model - a case study of Zhengzhou, China

Rapid global urban expansion necessitates accurate simulations to comprehend future growth patterns and their implications. Cellular automata, such as the widely used patch-generating land use simulation (PLUS) model, ensure reliable accuracy in urban growth simulations. However, previous studies have overlooked the development heterogeneity amongst sub-regions by treating the study area as the homogenous. Based on the PLUS model, this study introduces a new model coupling regional development heterogeneity and noise reduction (RDHNR-PLUS), which is an enhanced model that incorporates relative development coefficients derived from nighttime light data to capture regional heterogeneity. It also employs noise reduction techniques inspired by image classification's small patch processing method. Results demonstrate that the relative development coefficients effectively reveal the potential of different regions, while the noise reduction process mitigates simulation noise. The combined approach enhances overall accuracy, figure of merit, and structural similarity by 4.56 %, 20.44 %, and 5.06 %, respectively. Additionally, we simulate and analyse the built-up area of Zhengzhou from 2000 to 2030. The findings indicate rapid past growth, particularly in new urban areas, with projected future expansion likely to slow down. However, built-up areas dominated by medium to high and high densities will occupy three-quarters of the region. These results underscore the sustainability challenges faced by Zhengzhou, including disaster risk, traffic congestion, and air and noise pollution.

Adaptive modeling of satellite-derived nighttime lights time-series for tracking urban change processes using machine learning

Remotely sensed nighttime lights (NTL) uniquely capture urban change processes that are important to human and ecological well-being, such as urbanization, socio-political conflicts and displacement, impacts from disasters, holidays, and changes in daily human patterns of movement. Though several NTL products are global in extent, intrinsic city-specific factors that affect lighting, such as development levels, and social, economic, and cultural characteristics, are unique to each city, making the urban processes embedded in NTL signatures difficult to characterize, and limiting the scalability of urban change analyses. In this study, we propose a data-driven approach to detect urban changes from daily satellite-derived NTL data records that is adaptive across cities and effective at learning city-specific temporal patterns. The proposed method learns to forecast NTL signatures from past data records using neural networks and allows the use of large volumes of unlabeled data, eliminating annotation effort. Urban changes are detected based on deviations of observed NTL from model forecasts using an anomaly detection approach. Comparing model forecasts with observed NTL also allows identifying the direction of change (positive or negative) and monitoring change severity for tracking recovery. In operationalizing the model, we consider eleven urban areas from diverse geographic regions with dynamic NTL time-series and demonstrate the generalizability of the approach for detecting the change processes with different drivers and rates occurring within these urban areas based on NTL deviation. The proposed approach for monitoring changes from daily remote sensing observations efficiently utilizes large data volumes to support continuous monitoring and decision making.