Predicting the impacts of land use/land cover changes on seasonal urban thermal characteristics using machine learning algorithms

Kafy, Abdulla Al; Saha, Milan; Faisal, Abdullah-Al-; Rahaman, Zullyadini A.; Rahman, Muhammad Tauhidur; Liu, Desheng; Fattah, Md. Abdul; Rakib, Abdullah Al; Al-Dousari, Ahmad; Rahaman, Sk Nafiz; Hasan, Md Zakaria; Ahasan, Md Ahasanul Karim

doi:10.1016/j.buildenv.2022.109066

Cited by 79 publications

(16 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A dramatic increase in land use due to urbanization influences the hydrological regime by increasing runoff into impervious surfaces. LULC simulations involve modeling time series by incorporating previous land use classification datasets and other driving factors (Qian et al 2020;Karimi et al 2021;Kafy et al 2022). For this, LULCC has attracted growing interest in recent years, as it is a complex issue that involves physical, environmental, and socioeconomic factors (Aburas et al 2019).…”

Section: Future Lulc Predictionmentioning

confidence: 99%

Predicting LULC changes and assessing their impact on surface runoff with machine learning and remote sensing data.

Riche,

Drias,

Ricci

et al. 2023

Preprint

View full text Add to dashboard Cite

This study employs an approach to examine the influence of urbanization-induced land use changes on surface runoff. The research leverages the SCS-CN method, integrating remote sensing and machine learning, to analyze land use and cover (LULC) changes over the years 2000 to 2040. Initial land use classification (2000–2020) utilizes the SVM algorithm, while a novel temporal approach is applied to predict LULC for the years 2025, 2030, and 2040. The accuracy of the LULC prediction model is demonstrated to be 85.05% using the Random Forest (RF) algorithm. Notably, built-up areas increase from 11.73% (2000) to 32.96% (2040), whereas cultivated land and grassland decrease from 46.50–26.67%. The study further utilizes the SCS-CN method to model runoff for precipitation return periods of 5, 10, and 20 years, calculating Curve Number (CN) values. The results reveal variations in runoff patterns across different LULC classes and time periods. Higher return periods are associated with expanded runoff areas, with built-up areas contributing to runoff, while forests mitigate it. The study identifies that land factors, such as interception and permeability, exhibit limited influence during intense rainfall events, primarily due to capacity and saturation constraints. These findings have important implications for water resource management and strategies related to flood risk mitigation, benefiting governmental officials, planners, environmental experts, and hydraulic engineers. It's worth noting that a case study in Algeria was selected for its data availability.

show abstract

Section: Future Lulc Predictionmentioning

confidence: 99%

Predicting LULC changes and assessing their impact on surface runoff with machine learning and remote sensing data.

Riche,

Drias,

Ricci

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…To determine the relationship between UTFVI and LULC, UTFVI values were divided into 6 classes (i.e., none, weak, medium, strong, stronger, and strongest), according to the well-consolidated thresholds derived in [24,40] and reported in Table 2. Moreover, the table reports the correspondence of each UTFVI class with the class of the ecological evaluation index.…”

Section: Satellite Image Collection and Pre-processingmentioning

confidence: 99%

“…Once calculated, various methods can be used to characterize LST. Kafy et al [ 24 ] evaluated the LST of Sylhet city, Bangladesh, with Landsat images from 1995 to 2020, by employing the Urban Thermal Field Variance Index (UTFVI). Furthermore, Renard et al [ 25 ] demonstrated that the UTFVI is an efficient index to quantitatively analyze the urban heat island effect.…”

Section: Introductionmentioning

confidence: 99%

Unveiling the Dynamics of Thermal Characteristics Related to LULC Changes via ANN

Khachoo

Cutugno

Robustelli

et al. 2023

Sensors

View full text Add to dashboard Cite

Continuous and unplanned urbanization, combined with negative alterations in land use land cover (LULC), leads to a deterioration of the urban thermal environment and results in various adverse ecological effects. The changes in LULC and thermal characteristics have significant implications for the economy, climate patterns, and environmental sustainability. This study focuses on the Province of Naples in Italy, examining LULC changes and the Urban Thermal Field Variance Index (UTFVI) from 1990 to 2022, predicting their distributions for 2030. The main objectives of this research are the investigation of the future seasonal thermal characteristics of the study area by characterizing land surface temperature (LST) through the UTFVI and analyzing LULC dynamics along with their correlation. To achieve this, Landsat 4-5 Thematic Mapper (TM) and Landsat 9 Operational Land Imager (OLI) imagery were utilized. LULC classification was performed using a supervised satellite image classification system, and the predictions were carried out using the cellular automata-artificial neural network (CA-ANN) algorithm. LST was calculated using the radiative transfer equation (RTE), and the same CA-ANN algorithm was employed to predict UTFVI for 2030. To investigate the multi-temporal correlation between LULC and UTFVI, a cross-tabulation technique was employed. The study’s findings indicate that between 2022 and 2030, there will be a 9.4% increase in built-up and bare-land areas at the expense of the vegetation class. The strongest UTFVI zone during summer is predicted to remain stable from 2022 to 2030, while winter UTFVI shows substantial fluctuations with a 4.62% decrease in the none UTFVI zone and a corresponding increase in the strongest UTFVI zone for the same period. The results of this study reveal a concerning trend of outward expansion in the built-up area of the Province of Naples, with central northern regions experiencing the highest growth rate, predominantly at the expense of vegetation cover. These predictions emphasize the urgent need for proactive measures to preserve and protect the diminishing vegetation cover, maintaining ecological balance, combating the urban heat island effect, and safeguarding biodiversity in the province.

show abstract

“…Any city’s urban heat island (UHI) effect can be accurately described using the UTFVI. The purpose of this research is to evaluate the climate of Sylhet, a city in Bangladesh, by assessing and forecasting the seasonal (summer and winter) UTFVI scenario (Kafy et al 2022b ).…”

Section: Introductionmentioning

confidence: 99%

Quantitative assessment of land surface temperature and vegetation indices on a kilometer grid scale

Kikon

Kumar

Ahmed

2023

Environ Sci Pollut Res

View full text Add to dashboard Cite

Due to expanding populations and thriving economies, studies into the built environment’s thermal characteristics have increased. This research tracks and predicts how land use and land cover (LULC) changes may affect ground temperatures, urban heat islands, and city thermal fields (UTFVI). The current study examines land surface temperature (LST), urban thermal field variance index (UTFVI), normalized difference built-up index (NDBI), normalized difference vegetation index (NDVI), and land use land cover (LULC) on a kilometer scale. According to the comparative study, the mean LST decreases by 3 °C and the NDVI increases considerably. Correlation analysis showed that LST and NDVI are inversely connected, while LST and NDBI are positively correlated. NDVI and NDBI have a strong negative association, while LST and UTFVI have a positive correlation. Urban planners and environmentalists can study the LST’s effects on land surface parameters in different environmental contexts during the lockout period. The urban heat island (UHI) phenomenon, in which the land surface qualities of an urban region cause a change in the urban thermal environment, forms and intensifies over an urban area. The minimum and maximum LST in grid number 1 in 2009 was 20.30 °C and 29.91 °C, respectively, with a mean LST of 25.1 °C. There was a decline in the minimum and maximum LST in grid number 1 in 2020 with a minimum and maximum LST of 17.31 °C and 25.35 °C, respectively, with a mean LST of 21.33 °C. There was a 3.8 °C drop in the LST of this grid. The minimum and maximum NDVI were also − 0.16 and 0.59, respectively, with an average NDVI value of 0.21. Therefore, it is essential to evaluate and foresee the impact of LULC change on the thermal environment and examines the connection between LULC shifts with subsequent changes in land surface temperature (LST) along with the UHI phenomenon. Maps of the UTFVI reveal positive UHI phenomena, with the highest UTFVI zones occurring over the developed area and none over the adjacent rural territory. During the summer months, the urban area with the strongest UTFVI zone grows noticeably larger than it does during the winter months during the forecasted years. Future policymakers and city planners can mitigate the effects of heat stress and create more sustainable urban environments by evaluating the expected distribution maps of LULC, LST, UHI, and UTFVI.

show abstract

Predicting the impacts of land use/land cover changes on seasonal urban thermal characteristics using machine learning algorithms

Cited by 79 publications

References 38 publications

Predicting LULC changes and assessing their impact on surface runoff with machine learning and remote sensing data.

Predicting LULC changes and assessing their impact on surface runoff with machine learning and remote sensing data.

Unveiling the Dynamics of Thermal Characteristics Related to LULC Changes via ANN

Quantitative assessment of land surface temperature and vegetation indices on a kilometer grid scale

Contact Info

Product

Resources

About