Harnessing TabTransformer Model and Particle Swarm Optimization Algorithm for Remote Sensing-Based Heatwave Susceptibility Mapping in Central Asia
This study pioneers a fully remote sensing-based framework for mapping heatwave susceptibility, integrating the TabTransformer deep learning model with Particle Swarm Optimization (PSO) for robust hyperparameter tuning. The central question addressed is whether a fully remote sensing-driven, PSO-optimized TabTransformer can achieve accurate, scalable, and spatially detailed heatwave susceptibility mapping in data-scarce regions such as Central Asia. Utilizing ERA5-derived heatwave evidence and thirteen environmental and socio-economic predictors, the workflow produces high-resolution susceptibility maps spanning five Central Asian countries. Comparative analysis evidences that the PSO-optimized TabTransformer model outperforms the baseline across multiple metrics. On the test set, the optimized model achieved an RMSE of 0.123, MAE of 0.034, and R2 of 0.938, outperforming the standalone TabTransformer (RMSE = 0.132, MAE = 0.038, R2 = 0.93). Discriminative capacity also improved, with AUROC increasing from 0.933 to 0.940. The PSO-tuned model delivered faster convergence, lower final loss, and more stable accuracy during training and validation. Spatial outputs reveal heightened susceptibility in southern and southwestern sectors—Turkmenistan, Uzbekistan, southern Kazakhstan, and adjacent lowlands—with statistically significant improvements in spatial precision and class delineation confirmed by Chi-squared, Friedman, and Wilcoxon tests, all with congruent p-values of <0.0001. Feature importance analysis consistently identifies maximum temperature, frequency of hot days, and rainfall as dominant predictors. These advancements validate the potential of data-driven, deep learning approaches for reliable, scalable environmental hazard assessment, crucial for climate adaptation planning in vulnerable regions.
148
- 10.1038/s41467-021-26050-z
- Oct 4, 2021
- Nature Communications
24
- 10.3390/en14051451
- Mar 7, 2021
- Energies
1
- 10.1109/jstars.2024.3481460
- Jan 1, 2024
- IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
33
- 10.1038/s41591-024-02880-4
- Mar 25, 2024
- Nature medicine
110
- 10.1002/2013eo130001
- Mar 26, 2013
- Eos, Transactions American Geophysical Union
1
- 10.1029/2024ef005595
- Mar 1, 2025
- Earth's Future
7
- 10.1038/s41598-024-70634-w
- Aug 22, 2024
- Scientific Reports
84
- 10.1016/j.uclim.2018.12.010
- Jan 11, 2019
- Urban Climate
155
- 10.1007/s10113-014-0660-6
- Aug 9, 2014
- Regional Environmental Change
117
- 10.1021/acs.est.1c00024
- Apr 30, 2021
- Environmental science & technology
- Book Chapter
1
- 10.1007/978-3-030-63654-8_26
- Jan 1, 2021
Sustainable supply of energy and access to water are among the major issues facing the Central Asian and South Asian countries due to climate change. There is a need of an environmental friendly and cost-effective energy production technology to achieve reasonable energy production without affecting climate by release of any kind of greenhouse gases. This renewable and sustainable source of energy can be provided by floating photovoltaic systems/technology (FPVS) which also helps in achieving sustainable supply of clean water. This chapter discusses the working of Floating Photovoltaic (FPV) technology and its technical, economic and ecological feasibility over the land-based PV systems. It also discusses the prospects of implementing this technology in Central Asian, South Asian and South East Asian region by providing the case studies of already implemented systems in different parts of the world. The implementation of FPVS in Indus Basin, Kabul River Basin and water resources in Central Asian Countries, South Asian and South East Asian Countries can prove to be greatly effective by controlling huge amount of evaporation and precipitation and can prevent climate change in this region at bigger scale.KeywordsRenewable energyFloating photovoltaic systemsFeasibilityCentral AsiaSouth Asia
- Research Article
11
- 10.1016/j.envc.2021.100365
- Nov 10, 2021
- Environmental Challenges
Simulation of future land surface temperature under the scenario of climate change using remote sensing & GIS techniques of northwestern Rajshahi district, Bangladesh
- Research Article
3
- 10.26425/1816-4277-2023-7-162-170
- Sep 4, 2023
- Vestnik Universiteta
The article examines the factors and the scale of a forced emigration’s new wave from Russia to Central Asian countries. Wages in Central Asian countries are one of the factors in attracting highly qualified specialists from Russia. Such factors also include the potential of Russian IT-specialists in Central Asian countries and the policy of Central Asian countries to attract and retain IT-specialists from Russia. Emigration from Russia to Central Asian countries is a new wave of forced emigration. Various categories of people are leaving Russia: from ordinary emigrants to highly qualified specialists and also IT specialists. The active policy of the Central Asian countries to attract and retain specialists from Russia, as well as the visa-free regime between the Central Asian countries and Russia played a big role in choosing countries for the professionals’ migration from Russia. For the Central Asian country this is a new impetus for the development of an innovative economy. The article purpose is to identify the features of forced emigration from Russia to the Central Asian countries that are Commonwealth of Independent States’ members, as well as the prospects for using the potential of IT specialists in the development of Central Asian member countries of Commonwealth of Independent States.
- Research Article
73
- 10.1007/s11442-018-1513-x
- May 28, 2018
- Journal of Geographical Sciences
This paper uses data for the period 1950–2050 compiled by the United Nations Population Division together with methods including spatial autocorrelation analysis, hierarchical cluster analysis and the standard deviational ellipse, to analyze the spatio-temporal evolution of population and urbanization in the 75 countries located along the routes of the Silk Road Economic Belt and the 21st-century Maritime Silk Road, to identify future population growth and urbanization hotspots. The results reveal the following: First, in 2015, the majority of Belt and Road countries in Europe, South Asia and Southeast Asia had high population densities, whereas most countries in Central Asia, North Africa and West Asia, as well as Russia and Mongolia, had low population densities; the majority of countries in South Asia, Southeast Asia, Central Asia, West Asia and North Africa had rapid population growth, whereas many countries in Europe had negative population growth; and five Belt and Road countries are in the initial stage of urbanization, 44 countries are in the acceleration stage of urbanization, and 26 are in the terminal stage of urbanization. Second, in the century from 1950 to 2050, the mean center of the study area’s population is consistently located in the border region between India and China. Prior to 2000, the trajectory of the mean center was from northwest to southeast, but from 2000 it is on a southward trajectory, as the population of the study area becomes more concentrated. Future population growth hotspots are predicted to be in South Asia, West Asia and Southeast Asia, and hotspot countries for the period 2015–2030 include India, China, Pakistan and Indonesia, though China will move into negative population growth after 2030. Third, the overall urban population of Belt and Road countries increased from 22% in 1950 to 49% in 2015, and it is expected to gradually catch up with the world average, reaching 64% in 2050. The different levels of urbanization in different countries display significant spatial dependency, and in the hundred-year period under consideration, this dependency increases before eventually weakening. Fourth, between 2015 and 2030, urban population hotspots will include Thailand, China, Laos and Albania, while Kuwait, Cyprus, Qatar and Estonia will be urban “coldspots.” Fifth, there were 293 cities with populations over 1 million located along the Belt and Road in 2015, but that number is expected to increase to 377 by 2030. Of those, 43 will be in China, with many of the others located in India, Indonesia and the eastern Mediterranean.
- Research Article
- 10.63476/atjss.v1i1.50
- Dec 10, 2024
- ATJSS
The geopolitical location of Afghanistan is crucial for Central Asian and South Asian countries, as it provides opportunities and challenges for connectivity. Afghanistan's geopolitical location is significant in the Central Asian Era, as bordering countries exploit its natural resources, rivers, and possibilities. Afghanistan was the only mandatory corridor for empires like Genghis Khan, the Safavids, the Alexandrians, the British, the Russians, and the USA. The geopolitical location of Afghanistan has been a significant factor in regional cooperation organizations, reducing turbulences in the region. The study explores the opportunities and challenges in the area, identifying the challenges among these countries to prevent regional connectivity. The country's geographical location has been a significant factor in the development of technologies and weapons, making it a vital region for regional and international actors. The study highlights the importance of Afghanistan's geopolitical location in the connectivity of Central Asia, South Asia, and Middle Eastern countries. The study aims to identify the opportunities and challenges for Afghanistan in regional connectivity, identifying regional challenges, and identifying solutions for enhancing connectivity in relations with these countries. The study is important for political scholars, researchers, politicians, and policymakers. Afghanistan's geopolitical location in Asia is vital for Central Asian and South Asian countries. The results show that Afghanistan has an important impact on the Central Asian Era regarding geopolitics; all these countries, especially the bordering countries, are taking advantage of the natural resources, rivers, and possibilities of the North-Northeast and western parts of Afghanistan.
- Research Article
- 10.63476/atjss.v1i1.64
- Dec 9, 2024
- ATJSS
The geopolitical location of Afghanistan is crucial for Central Asian and South Asian countries, as it provides opportunities and challenges for connectivity. Afghanistan's geopolitical location is significant in the Central Asian Era, as bordering countries exploit its natural resources, rivers, and possibilities. Afghanistan was the only mandatory corridor for empires like Genghis Khan, the Safavids, the Alexandrians, the British, the Russians, and the USA. The geopolitical location of Afghanistan has been a significant factor in regional cooperation organizations, reducing turbulences in the region. The study explores the opportunities and challenges in the area, identifying the challenges among these countries to prevent regional connectivity. The country's geographical location has been a significant factor in the development of technologies and weapons, making it a vital region for regional and international actors. The study highlights the importance of Afghanistan's geopolitical location in the connectivity of Central Asia, South Asia, and Middle Eastern countries. The study aims to identify the opportunities and challenges for Afghanistan in regional connectivity, identifying regional challenges, and identifying solutions for enhancing connectivity in relations with these countries. The study is important for political scholars, researchers, politicians, and policymakers. Afghanistan's geopolitical location in Asia is vital for Central Asian and South Asian countries. The results show that Afghanistan has an important impact on the Central Asian Era regarding geopolitics; all these countries, especially the bordering countries, are taking advantage of the natural resources, rivers, and possibilities of the North-Northeast and western parts of Afghanistan. Keywords: Geopolitical Location,Afghanistan,South Asia,Central Asia,Connectivity,Opportunities,Challenges
- Research Article
14
- 10.3390/rs13020313
- Jan 18, 2021
- Remote Sensing
Central Asia is prone to wildfires, but the relationship between wildfires and climatic factors in this area is still not clear. In this study, the spatiotemporal variation in wildfire activities across Central Asia during 1997–2016 in terms of the burned area (BA) was investigated with Global Fire Emission Database version 4s (GFED4s). The relationship between BA and climatic factors in the region was also analyzed. The results reveal that more than 90% of the BA across Central Asia is located in Kazakhstan. The peak BA occurs from June to September, and remarkable interannual variation in wildfire activities occurs in western central Kazakhstan (WCKZ). At the interannual scale, the BA is negatively correlated with precipitation (correlation coefficient r = −0.66), soil moisture (r = −0.68), and relative humidity (r = −0.65), while it is positively correlated with the frequency of hot days (r = 0.37) during the burning season (from June to September). Composite analysis suggests that the years in which the BA is higher are generally associated with positive geopotential height anomalies at 500 hPa over the WCKZ region, which lead to the strengthening of the downdraft at 500 hPa and the weakening of westerlies at 850 hPa over the region. The weakened westerlies suppress the transport of water vapor from the Atlantic Ocean to the WCKZ region, resulting in decreased precipitation, soil moisture, and relative humidity in the lower atmosphere over the WCKZ region; these conditions promote an increase in BA throughout the region. Moreover, the westerly circulation index is positively correlated (r = 0.53) with precipitation anomalies and negatively correlated (r = −0.37) with BA anomalies in the WCKZ region during the burning season, which further underscores that wildfires associated with atmospheric circulation systems are becoming an increasingly important component of the relationship between climate and wildfire.
- Book Chapter
2
- 10.4018/978-1-5225-4032-8.ch002
- Jan 1, 2018
China is one of the fastest growing economies in the world. To ensure a continual increase in trade, China's contemporary policies are aimed at the creation of new market opportunities for China's companies abroad. The chapter addresses the major challenges of collaboration between China and the countries of Central and Northeast Asia, reviews the milestones of China's trade policies in Eurasia, analyses China's recent trade and development initiative (One Belt One Road project) and its convergence with other integration initiatives in the region, and reviews trade flows between China and the countries of Central Asia (Kazakhstan, Kyrgyzstan, Russia, Tajikistan, Turkmenistan, and Uzbekistan) and Northeast Asia (Democratic People's Republic of Korea, Japan, Mongolia, and the Republic of Korea) during 2015. The chapter is concluded with an analysis of how China can pursue shaping an inter-regional market by looking across national boundaries and with the discussion of structural changes needed for China to ensure its competitiveness in the markets of the studied country.
- Research Article
- 10.1016/j.sbspro.2014.02.123
- Mar 1, 2014
- Procedia - Social and Behavioral Sciences
Regional and Geo-Economic Situation in the Turkic – Speaking Countries in Central Asia
- Research Article
- 10.1051/e3sconf/202020904001
- Jan 1, 2020
- E3S Web of Conferences
Results of the next round of studies on Russian interstate electric ties are described. A part of the Eurasian region including European and Siberian part of Russia and countries of Central Asia, Caucasus, Southern Asia and Middle East is considered for 2040 target year. Great effectiveness of creation of interstate power grid in this region is shown.
- Preprint Article
- 10.5194/egusphere-egu25-11240
- Mar 18, 2025
Accurate streamflow prediction is critical for flood forecasting and water resource management, particularly in data-scarce regions like Central Asia (CA), where traditional hydrological models struggle due to insufficient discharge data. Deep learning models, such as Long Short-Term Memory (LSTM), have demonstrated the potential for global hydrologic regionalization by leveraging both climate data and catchment characteristics. We used a transfer learning (TL) approach to improve streamflow predictions by first pretraining LSTM models on catchments from data-rich regions like Switzerland, Scotland, and British Columbia (source regions). These deep learning models were then fine-tuned on the data scarce target region (CA basins). This approach leverages the knowledge gained from the source regions to adapt the model to the target region, enhancing prediction accuracy despite the data scarcity in CA. Incorporating lagged streamflow alongside ERA-5 climate data boosted prediction accuracy, particularly in snowmelt and glaciers influenced basins like Switzerland (median NSE=0.707 to 0.837), British Columbia (median NSE= 0.775 to 0.923) and CA (median NSE=0.693 to 0.798). K-Means algorithm was applied to categorize catchments from four global locations into five clusters (labeled 0&#8211;4) based on their specific attributes. The predictive performance of fine-tuned LSTM model has significantly enhanced when leveraging a pre-trained model with cluster 2, as demonstrated by higher median metrics (NSE=0.958, KGE=0.905, RMSE=10.723, MSE=115.055) compared to both the locally trained model (NSE=0.851, KGE=0.792, RMSE=20.377, MSE=415.579) and individual basin-based training approaches (NSE=0.69, KGE=0.692, RMSE=25.563, MSE=676.110). These results highlight the effectiveness of pretraining the LSTM model on diverse clusters (0, 1, 2, and 4) before fine-tuning on the target region (cluster 3). Moreover, pretraining the LSTM model with clusters 0 and 4 resulted in enhanced performance by increasing the number of basins, whereas the impact was minimal or even declined when using clusters 1 and 2, as well as when all basins from the four clusters were included. These findings demonstrate the feasibility of transfer learning in addressing data scarcity challenges and underscore the importance of diverse and high-quality training data in developing robust, regionalized hydrological models. This approach bridges the gap between data-rich and data-scarce regions, offering a pathway to improved flood prediction and water resource management.
- Book Chapter
- 10.18574/nyu/9781479844333.003.0010
- Dec 31, 2020
10. India’s Objectives in Central Asia
- Book Chapter
1
- 10.1007/978-981-13-6814-1_5
- Jan 1, 2019
This study aims to define why mineral-resource-rich landlocked developing countries (LLDCs) in Central Asia are less attractive than other regions for foreign investors. The results show that a higher return on capital, openness, and good quality of infrastructure promotes foreign direct investment (FDI) in LLDCs in Central Asia. However, a decline in corruption has a positive effect on FDI, while regulatory quality and degree of business freedom have insignificant impacts on investment. Remarkably, political instability, corporate tax rate, and inflation have a positive impact on FDI. LLDCs in Central Asia are likely to have a weak and inefficient decision-making process, which would eventually attract investors trying to seize opportunities. These results reveal that political instability, a high corporate tax rate, and a high inflation rate do not always lead to less FDI flow.
- Research Article
12
- 10.1186/s13071-022-05477-3
- Sep 29, 2022
- Parasites & Vectors
BackgroundThe Silk Road connected the East and West for over 1500 years. Countries in Central Asia are valuable in addressing the hypothesis that parasites on domestic animals were introduced along the Silk Road. Adult fleas are obligate parasites, having worldwide distribution. In dogs, Ctenocephalides canis, C. felis and C. orientis are the most common species identified. The distribution of the Oriental cat flea, C. orientis, is restricted to southeast Asia. The purpose of this study was to determine the diversity of dog fleas from Uzbekistan, a country in Central Asia, with particular reference to C. orientis.MethodsFleas were collected from 77 dogs from 5 locations in Uzbekistan. The cox1 gene sequences from Ctenocephalides spp. were compared to global collection of Ctenocephalides cox1 haplotypes. Landmark-based geometric morphometrics have been applied to the head and curvature to compare C. canis and C. canis using canonical variate analysis and discriminant function analysis.ResultsOverall, 199 fleas were collected and identified as C. canis (n = 115, 58%), C. orientis (n = 53, 27%) and Pulex irritans (n = 22, 11%). None of the fleas were C. felis. All Ctenocephalides spp. fleas were subject to cox1 amplification and 95% (166/175) yielded DNA sequence. There were 25 cox1 haplotypes; 14 (22/25, 88%) were C. canis cox1 haplotypes and 3 (3/25, 12%) were C. orientis cox1 haplotypes. Molecular analysis confirmed the absence of C. felis. Four (4/22) and one (1/3) cox1 haplotypes were identical to cox1 haplotypes belonging to C. canis and C. orientis cox1 haplotypes identified elsewhere, respectively. Overall morphometric analysis confirmed significant differences between the head shape of C. canis and C. orientis and improved four–fivefold the species identification compared to traditional morphological key.ConclusionWe report for the first time the presence of C. orientis in Uzbekistan. Differentiation of C. orientis from C. canis and C. felis remains difficult in regions where these species coexist. Studies in Central and Southeast Asia should confirm species identity using cox1 locus to enable retracing of the distribution of the Ctenocephalides in Asia. The presence of C. orientis suggests that this species may have been introduced from the east along the ancient Silk Road.Graphical
- Research Article
2
- 10.1177/18793665221124814
- Aug 1, 2022
- Journal of Eurasian Studies
Russia’s invasion of Ukraine will have political and economic impacts in Central Asia. Politically, first, Central Asian countries will strengthen cooperation with neighbouring regional powers such as India, Turkey and Iran to hedge their political and economic security. Second, while China’s influence in Central Asia will increase, SCO will be more economic cooperation organisation. Third, the future direction of Central Asian regionalism will be uncertain. Although it is unlikely, if Uzbekistan shows anti-Russian behaviour, regionalism in Central Asia may weaken. Fourth, it is unlikely that the US role will be expanded again in Central Asia after the Ukraine War. Economically, first, it is highly likely that the status and centripetal force of the Eurasian Economic Union will be weakened. Second, if Europe’s anti-Russian energy policy is strengthened and green energy policies are accelerated, the renewable energy policies of Central Asian carbon-centered energy producing countries such as Kazakhstan in particular can be accelerated. Third, if the logistical obstacles of TSR persist, the bypass logistics infrastructure going to Central Asia through India, Iran, Pakistan, etc. instead of through Russia will be activated. It seems inevitable to shift Korea’s diplomacy toward Central Asia to a certain level to organically link value-based diplomacy and economic security strategies. In this context, first, the existing diplomatic strategies and economic cooperation policies toward Central Asia must be freed from the tendency to view Central Asian countries only as a sphere of influence from Russia. Second, in a situation in which economic cooperation between Korea and Russia is inevitably severely curtailed due to western sanctions against Russia and geopolitical conflicts, it is necessary to strengthen economic cooperation with Central Asian countries as a means of circumventing economic cooperation with Russia. Third, there is a possibility that the northern policy of new governments may be weakened due to the Russia’s invasion of Ukraine, thus the cooperation with Central Asian countries may also shrink. It will be necessary to maintain and develop the previous government’s cooperation platform with Central Asian countries.
- New
- Research Article
- 10.3390/atmos16111265
- Nov 6, 2025
- Atmosphere
- New
- Research Article
- 10.3390/atmos16111263
- Nov 5, 2025
- Atmosphere
- New
- Research Article
- 10.3390/atmos16111264
- Nov 5, 2025
- Atmosphere
- Research Article
- 10.3390/atmos16111262
- Nov 4, 2025
- Atmosphere
- Research Article
- 10.3390/atmos16111260
- Nov 3, 2025
- Atmosphere
- Research Article
- 10.3390/atmos16111261
- Nov 3, 2025
- Atmosphere
- Research Article
- 10.3390/atmos16111259
- Nov 2, 2025
- Atmosphere
- Research Article
- 10.3390/atmos16111258
- Nov 2, 2025
- Atmosphere
- Research Article
- 10.3390/atmos16111256
- Oct 31, 2025
- Atmosphere
- Research Article
- 10.3390/atmos16111255
- Oct 31, 2025
- Atmosphere
- Ask R Discovery
- Chat PDF
AI summaries and top papers from 250M+ research sources.