Spatio-Temporal Change of Dispersal Areas of Greater Kudu (Tragelaphus strepsiceros) in Lake Bogoria Landscape, Kenya

Decline in wildlife populations is manifest globally, regionally and locally. A wildlife decline of 68% has been reported in Kenya’s rangelands with Baringo County experiencing more than 85% wildlife loss in the last four decades. Greater Kudu (Tragelaphus strepsiceros) is endemic to Lake Bogoria landscape in Baringo County and constitutes a major tourist attraction for the region necessitating use of its photo on the County’s logo and thus a flagship species. Tourism plays a central role in Baringo County’s economy and is a major source of potential growth and employment creation. The study was carried out to assess spatio-temporal change of dispersal areas of Greater Kudu (GK) in Lake Bogoria landscape in the last four years for enhanced adaptive management and improved livelihoods. GK population distribution primary data collected in December 2022 and secondary data acquired from Lake Bogoria National Game Reserve (LBNGR) for 2019 and 2020 were digitized using in a Geographic Information System (GIS). Measures of dispersion and point pattern analysis (PPA) were used to analyze dispersal of GK population using GIS. Spatio-temporal change of GK dispersal in LBNR was evident thus the null hypothesis was rejected. It is recommended that anthropogenic activities contributing to GK’s habitat degradation be curbed by providing alternative livelihood sources and promoting community adoption of sustainable technologies for improved livelihoods.

Spatio-Temporal Changes in the Rice Planting Area and Their Relationship to Climate Change in Northeast China: A Model-Based Analysis

Rice is one of the most important grain crops in Northeast China （NEC） and its cultivation is sensitive to climate change. This study aimed to explore the spatio-temporal changes in the NEC rice planting area over the period of 1980-2010 and to analyze their relationship to climate change. To do so, the CLUE-S （conversion of land use and its effects at small region extent） model was ifrst updated and used to simulate dynamic changes in the rice planting area in NEC to understand spatio-temporal change trends during three periods： 1980-1990, 1990-2000 and 2000-2010. The changing results in individual periods were then linked to climatic variables to investigate the climatic drivers of these changes. Results showed that the NEC rice planting area expanded quickly and increased by nearly 4.5 times during 1980-2010. The concentration of newly planted rice areas in NEC constantly moved northward and the changes were strongly dependent on latitude. This conifrmed that climate change, increases in temperature in particular, greatly inlfuenced the shift in the rice planting area. The shift in the north limit of the NEC rice planting area generally followed a 1＆#176;C isoline migration pattern, but with an obvious time-lag effect. These ifndings can help policy makers and crop producers take proper adaptation measures even when exposed to the global warming situation in NEC.

Spatio-Temporal Changes of Soil Salinity in Arid Areas of South Xinjiang Using Electromagnetic Induction

The aim of this paper was to research the spatio-temporal changes in total soluble salt content （TS） in a typical arid region of South Xinjiang, China, where the climate is arid and soil salinization happens easily. The total soluble salt content was interpreted by measurements made in the horizontal mode with EM38 and EM31. The electromagnetic induction （EM） surveys were made three times with the apparent soil electrical conductivity （ECa） measurements taken at 3 873 locations in Nov. 2008, 4 807 locations in Apr. 2009 and 6 324 locations in Nov. 2009, respectively. For interpreting the ECa measurements into total soluble salt content, calibtion sites were needed for EM survey of each time, e.g., 66 sites were selected in Nov. 2008 to measure ECa, and soils-core samples were taken by different depth layers of 0-10, 10-20 and 20-40 cm at the same time. On every time duplicate samples were taken at five sites to allevaite the local-scale variability, and soil temperatures in different layers through the profiles were also measured. Factors including TS, pH, water content, bulk density were analyzed by lab experiments. ECa calibration equations were obtained by linear regression analysis, which indicated that soil salinity was one primary concern to ECa with a determination coefficient of 0.792 in 0-10 cm layer, 0.711 in 10-20 cm layer and 0.544 in 20-40 cm layer, respectively. The maps of spatial distribution were predicted by Kriging interpolation, which showed that the high soil salinity was located near the drainage canal, which validated the trend effect caused by the irrigation canal and the drainage canal. And by comparing the soil salinity in different layers, the soluble salt accumulated to the top soil surface only in the area where the soil salinization was serious, and in the other areas, the soil salinity trended to increase from the top soil surface to 40 cm depth. Temporal changes showed that the soil salinity in November was higher than that in April, and the soil salinization trended to aggravate, especially in the top soil layer of 0-10 cm.

Analysis of Spatio-Temporal Changes of Land Usein Xuzhou City Based on Remote Sensing

Based on the satellite remote sensing TM/ETM images of Xuzhou city, basic data about land use of the city from 1994 to 2000 are obtained with the neural network classification module of PCI software, and the dynamic con- version matrix of land use is thus calculated. The areas of construction land and water body have increased by 1833.93 hm2 and 804.87 hm2, respectively. On the contrary, the area of cropland has decreased by 3207.24 hm2. The area of cropland converted into construction land makes up 26.84%, and that converted into water body amounts for 8.17% of the total area of cropland in 1994. The variation index of land use degree and the dynamic degree index of land use computed are 1.38 and 57.81%, respectively, which demonstrate that land use in Xuzhou is in a development period and the changes are drastic. The frequency index and importance index of the form in which cropland converted into con- struction land are 29.91% and 68.93% respectively. The results indicate that the change is not only widespread in space but a major form of spatial change of land use in the area.

Spatio-temporal changes of exposure and vulnerability to floods in China

A socio-economic data set on China＇s historical flood losses for the period 1984--2012 was compiled to analyze the exposed population, economy, and crop area as well as the vulnerabilities of the population and economy to floods. The results revealed that the exposed population was approximately 126 persons km-2 per year when taking China as a whole; in terms of the economy, potential losses due to floods were estimated to be approximately 1.49 million C/W4 km 2 and the crop area exposed to floods covered 153 million hm2 per year. China＇s total exposure to floods significantly increased over the analysis period. The areas that showed the higher exposure were mainly located along the east coast. The population＇s vulnerability to floods showed a significantly increasing trend, however, the economic vulnerability showed a decreasing trend. The populations and economies that were most vulnerable to floods were in Hunan, Anhui, Chongqing, Jiangxi, and Hubei provinces. The municipalities of Shanghai, Beijing, and Tianjin showed the lowest vulnerabilities to floods.

Spatio-temporal Changes and Associated Uncertainties of CENTURYmodelled SOC for Chinese Upland Soils, 1980-2010

Detailed information on the spatio-temporal changes of cropland soil organic carbon(SOC) can significantly contribute to the improvement of soil fertility and mitigate climate change. Nonetheless, information and knowledge on the national scale spatio-temporal changes and the corresponding uncertainties of SOC in Chinese upland soils remain limited. The CENTURY model was used to estimate the SOC storages and their changes in Chinese uplands from 1980 to 2010. With the Monte Carlo method, the uncertainties of CENTURY-modelled SOC dynamics associated with the spatial heterogeneous model inputs were quantified. Results revealed that the SOC storage in Chinese uplands increased from 3.03(1.59 to 4.78) Pg C in 1980 to 3.40(2.39 to 4.62) Pg C in 2010. Increment of SOC storage during this period was 370 Tg C, with an uncertainty interval of –440 to 1110 Tg C. The regional disparities of SOC changes reached a significant level, with considerable SOC accumulation in the Huang-Huai-Hai Plain of China and SOC loss in the northeastern China. The SOC lost from Meadow soils, Black soils and Chernozems was most severe, whilst SOC accumulation in Fluvo-aquic soils, Cinnamon soils and Purplish soils was most significant. In modelling large-scale SOC dynamics, the initial soil properties were major sources of uncertainty. Hence, more detailed information concerning the soil properties must be collected. The SOC stock of Chinese uplands in 2010 was still relatively low, manifesting that recommended agricultural management practices in conjunction with effectively economic and policy incentives to farmers for soil fertility improvement were indispensable for future carbon sequestration in these regions.

Analysis on the Spatio-Temporal Changes of Sustainable Land Use in Tibet

By constructing evaluation indicator system of sustainable land use of Tibet from three aspects of ecological environment, economic development, resources and social advancement, this article studies the following contents respectively in two dimensions of time and space： the changes of sustainable land use of Tibet in recent 20 years and spatial characteristics of sustainable land use of Tibet in 2002. The following conclusions can be drawn from evaluation results .① With regard to com- prehensive evaluation value of sustainable land use, the trend of Tibet sustainable land use evaluation values from 1983 to 2002 are very close to the comprehensive evaluation values of ecological environment, which is up trend; ② sustainable utilization degree of land use in eastern region of Tibet is much higher than that of western region. ③ the sustainable land use evaluation value of Nyingtri County is the highest, and the counties with relatively higher land sustainable use values include Lhasa, Lhoka, Chamdo. While Nakchu, Ngari, Shigatse counties have the relatively lower evaluation values; ④ By analyzing each evaluation indicator＇s weight on sustainable land use, it can be concluded that the key limiting factors of sustainable Tibet land resource utilization are land desertification, grassland degradation and low economic level.

Analysis of spatio-temporal changes in forest biomass in China

Forests play a central role in the global carbon cycle.China's forests have a high carbon sequestration potential owing to their wide distribution,young age and relatively low carbon density.Forest biomass is an essential variable for assessing carbon sequestration capacity,thus determining the spatio-temporal changes of forest biomass is critical to the national carbon budget and to contribute to sustainable forest management.Based on Chinese forest inventory data(1999–2013),this study explored spatial patterns of forest biomass at a grid resolution of 1 km by applying a downscaling method and further analyzed spatiotemporal changes of biomass at different spatial scales.The main findings are:(1)the regression relationship between forest biomass and the associated infuencing factors at a provincial scale can be applied to estimate biomass at a pixel scale by employing a downscaling method;(2)forest biomass had a distinct spatial pattern with the greatest biomass occurring in the major mountain ranges;(3)forest biomass changes had a notable spatial distribution pattern;increase(i.e.,carbon sinks)occurred in east and southeast China,decreases(i.e.,carbon sources)were observed in the northeast to southwest,with the largest biomass losses in the Hengduan Mountains,Southern Hainan and Northern Da Hinggan Mountains;and,(4)forest vegetation functioned as a carbon sink during 1999–2013 with a net increase in biomass of 3.71 Pg.

Spatio-temporal changes of underground coal fires during 2008-2016 in Khanh Hoa coal field(North-east of Viet Nam) using Landsat time-series data

Underground coal fires are one of the most common and serious geohazards in most coal producing countries in the world. Monitoring their spatio-temporal changes plays an important role in controlling and preventing the effects of coal fires, and their environmental impact. In this study, the spatio-temporal changes of underground coal fires in Khanh Hoa coal field(North-East of Viet Nam) were analyzed using Landsat time-series data during the 2008-2016 period. Based on land surface temperatures retrieved from Landsat thermal data, underground coal fires related to thermal anomalies were identified using the MEDIAN+1.5×IQR(IQR: Interquartile range) threshold technique. The locations of underground coal fires were validated using a coal fire map produced by the field survey data and cross-validated using the daytime ASTER thermal infrared imagery. Based on the fires extracted from seven Landsat thermal imageries, the spatiotemporal changes of underground coal fire areas were analyzed. The results showed that the thermalanomalous zones have been correlated with known coal fires. Cross-validation of coal fires using ASTER TIR data showed a high consistency of 79.3%. The largest coal fire area of 184.6 hectares was detected in 2010, followed by 2014(181.1 hectares) and 2016(178.5 hectares). The smaller coal fire areas were extracted with areas of 133.6 and 152.5 hectares in 2011 and 2009 respectively. Underground coal fires were mainly detected in the northern and southern part, and tend to spread to north-west of the coal field.

Remote Sensing &GIS Based Spatio-Temporal Change Analysis of Wetland in Dhaka City, Bangladesh

Landscape of Dhaka city—one of the fastest growing mega cities in the world, is continuously changing due to un-planned urbanization. For example, the wetlands of the city have been shrinking. This study evaluates wetland changes in Dhaka Metropolitan Area (DMA), Bangladesh, between 1978 and 2009. Spatial and temporal dynamics of wetland changes were quantified using four Landsat images, a supervised classi?cation algorithm and the post-classi?cation change detection technique in GIS environment. Accuracy of the Landsat-derived wetland maps ranged from 87% to 92.5%. The analysis revealed that area of wetland and Rivers & Khals in Dhaka city decreased significantly over the last 30 years by 76.67% and 18.72% respectively. This changing trend of wetlands makes the drainage system of Dhaka City vulnerable, creating water logging problems and their consequences. Land filling and encroachment were recognized to be the main reasons for shrinking of the wetlands in the city. Development and alteration of the existing water bodies should consider the natural hydrological conditions.

Remote Sensing and GIS for the Spatio-Temporal Change Analysis of the East and the West River Bank Erosion and Accretion of Jamuna River (1995-2015), Bangladesh

Jamuna River is one of the principal rivers of Bangladesh, changing continuously due to erosion and accretion over the past decades. This analysis evaluates the East Bank and the West Bank erosion and accretion between 1996 and 2015 for Jamuna River. An unsupervised classification algorithm and post-classification change employing skills in Geographic Information System are performed to evaluate spatial and temporal dynamics of erosion and accretion for different points of Jamuna River using Bangladesh. Landsat image (1995, 2005, 2015). The correctness of the Landsat-produced map ranges from 82% to 84%. It has been evidently observed that changes in the proportion of erosion and accretion differ in different points of Jamuna River. The highest eroded area is 3.82 square kilometers (km2) during the period of 1995 to 2005 and the highest accreted area is 6.15 square kilometers (km2) during the period of 1995 to 2015. The erosion and accretion values fluctuated from place to place. The changing trend of Riverbank is creating many socio-economic problems in the proximate areas.

Integrated approach for understanding spatio-temporal changes in forest resource distribution in the central Himalaya

Intense anthropogenic exploitation has altered distribution of forest resources. This change was analyzed using visual interpretation of satellite data of 1979, 1999 and 2009. Field and interactive social surveys were conducted to identify spatial trends in forest degradation and data were mapped on forest cover and land use maps. Perceptions of villagers were compiled in a pictorial representation to understand changes in forest resource distribution in central Himalaya from 1970 to 2010. For- ested areas were subject to degradation and isolation due to loss of con- necting forest stands. Species like Lantana camara and Eupatorium adenophorum invaded forest landscapes. Intensity of human pressure differed by forest type and elevation. An integrated approach is needed to monitor forest resource distribution and disturbance.

Classification and Spatio-Temporal Change Detection of Land Use/Land Cover Using Remote Sensing and Geographic Information System in the Manouba Region, NE Tunisia

Land use/land cover (LULC) mapping and change detection are fundamental aspects of remote sensing data application. Therefore, selecting an appropriate classifier approach is crucial for accurate classification and change assessment. In the first part of this study, the performance of machine learning classification algorithms was compared using Landsat 9 image (2023) of the Manouba government (Tunisia). Three different classification methods were applied: Maximum Likelihood Classification (MLC), Support Vector Machine (SVM), and Random Trees (RT). The classification aimed to identify five land use classes: urban area, vegetation, bare area, water and forest. A qualitative assessment was conducted using Overall Accuracy (OA) and the Kappa coefficient (K), derived from a confusion matrix. The results of the land cover classification demonstrated a high level of accuracy. The SVM method exhibited the best performance, with an overall accuracy of 93% and a kappa accuracy of 0.9. The ML method is the second-best classifier with an overall accuracy of 92% and a kappa accuracy of 0.88. The Random Trees method yielded the lowest accuracy among the three approaches, with an overall accuracy of 91% and a kappa accuracy of 0.87. The second part of the study focused on analyzing LULC changes in the study area. Based on the classification results, the SVM method was chosen to classify the Landsat 7 image acquired in 2000. LULC changes from 2000 to 2023 were investigated using change detection comparison. The findings indicate that over the last 23 years, vegetation land and urban areas in the study area have experienced significant increases of 31.94% and 5.47%, respectively. This study contributed to a better understanding of the classification process and dynamic LULC changes in the Manouba region. It provided valuable insights for decision-makers in planning land conservation and management.

Assessing Spatio-Temporal Land Cover Changes in Dhund River Basin, Eastern Rajasthan (India), Using Multi-Temporal Landsat Data

Land cover is an impression of natural cover on surface of earth such as bare soil, river, grass etc. and utilization of these natural covers for various human needs and purposes by mankind is defined as land use. Land cover identification, delineation and mapping is important for planning activities, resource management and global monitoring studies while baseline mapping and subsequent monitoring is done by application of land use to get timely information about quantity of land that has been used. The present study has been carried out in Dhund river watershed of Jaipur, Rajasthan which covers an area of about 1828 sq∙km. The minimum and maximum elevation of the area is found to be 214 m and 603 m respectively. Land use and land cover changes of three decades from 1991 to 2021 have been interpreted by using remotes sensing and GIS techniques. ArcGIS software (Arc map 10.2), SOI topographic map, Cartosat-1 DEM and satellite data of Landsat 5 and Landsat 8 have been used for interpretation of eleven classes. The study shows an increase in cultivated land, settlement, waterbody, open forest, plantation and mining due to urbanization because of increasing demands of food, shelter and water while a decrease in dense forest, river, open scrub, wasteland and uncultivated land has also been marked due to destruction of aforementioned by anthropogenic activities such as industrialization resulting in environmental degradation that leads to air, soil and water pollution.

Spatio-temporal changes of NDVI and its relation with climatic variables in the source regions of the Yangtze and Yellow rivers

The source regions of the Yangtze and Yellow rivers are important water conservation areas of China. In recent years, ecological deterioration trend of the source regions caused by global climate change and unreasonable resource development increased gradually. In this paper, the spatial distribution and dynamic change of vegetation cover in the source regions of the Yangtze and Yellow rivers are analyzed in recent 10 years based on 1-km resolution multi-temporal SPOTVGT-DN data from 1998 to 2007. Meanwhile, the cor- relation relationships between air temperature, precipitation, shallow ground temperature and NDVI, which is 3x3 pixel at the center of Wudaoliang, Tuotuohe, Qumalai, Maduo, and Dari meteorological stations were analyzed. The results show that the NDVI values in these two source regions are increasing in recent 10 years. Spatial distribution of NDVI which was consistent with hydrothermal condition decreased from southeast to northwest of the source regions. NDVI with a value over 0.54 was mainly distributed in the southeastern source region of the Yellow River, and most NDVI values in the northwestern source region of the Yangtze River were less than 0.22. Spatial changing trend of NDVI has great difference and most parts in the source regions of the Yangtze and Yellow rivers witnessed indistinct change. The regions with marked increasing trend were mainly distributed on the south side of the Tongtian River, some part of Keqianqu, Tongtian, Chumaer, and Tuotuo rivers in the source region of the Yangtze River and Xingsuhai, and southern Dari county in the source region of the Yellow River. The regions with very marked increasing tendency were mainly distributed on the south side of Tongtian Rriver and sporadically distributed in hinterland of the source re- gion of the Yangtze River. The north side of Tangula Range in the source region of the Yangtze River and Dari and Maduo counties in the source region of the Yellow River were areas in which NDVI changed with marked decreasing tendency. The NDVI change was positively correlated with average temperature, precipitation and shallow ground temperature. Shallow ground temperature had the greatest effect on NDVI change, and the second greatest factor influencing NDVI was average temperature. The correlation between NDVI and shallow ground temperature in the source regions of the Yangtze and Yellow rivers increased significantly with the depth of soil layer.

Spatio-temporal distribution of net primary productivity along the northeast China transect and its response to climatic change

An improved Carnegie Ames Stanford Approach model （CASA model） was used to estimate the net primary productivity （NPP） of the Northeast China Transect （NECT） every month from 1982 to 2000. The spatial-temporal distribution of NPP along NECT and its response to climatic change were also analyzed. Results showed that the change tendency of NPP spatial distribution in NECT is quite similar to that of precipitation and their spatial correlation coefficient is up to 0.84 （P 〈 0.01）. The inter-annual variation of NPP in NECT is mainly affected by the change of the aestival NPP every year, which accounts for 67.6% of the inter-annual increase in NPP and their spatial correlation coefficient is 0.95 （P 〈 0.01）. The NPP in NECT is mainly cumulated between May and September, which accounts for 89.8% of the annual NPP. The NPP in summer （June to August） accounts for 65.9% of the annual NPP and is the lowest in winter. Recent climate changes have enhanced plant growth in NECT. The mean NPP increased 14.3% from 1980s to 1990s. The inter-annual linear trend of NPP is 4.6 gC·m^-2·a^-1, and the relative trend is 1.17%, which owns mainly to the increasing temperature.

Analysis of the Spatio-temporal Changes in Acid Rain and Their Causes in China(1998–2018)

With the rapid development of the economy,acid rain has become one of the major environmental problems that endanger human health.Being the largest developing country,the environmental problems caused by acid rain are of increasing concern with the rapid industrialization and urbanization in China.Recently,many researchers have focused on acid rain.To better understand the temporal and spatial dynamics of acid rain in China,the monitoring data on acid rain from 1998 to 2018 were studied using ArcGIS 10.2.The results show that the proportion of acid rain cities,the frequency,and the area of acid rain were decreasing,however,the situation still remains serious.Overall,the chemical type of acid rain was mainly sulfuric acid rain.However,the concentration ratio of SO_(4)^(2-)/NO_(3)^(-)-decreased by 81.90%in 2018 compared with 1998,and presented a decreasing trend,which indicates that the contribution of nitrate to precipitation acidity has been increasing year by year.This research will help us to understand the distribution characteristics and causes of acid rain in China,and it may provide an effective reference for the prevention and control of acid rain in China.

Where Are Potential Regions for the Reallocation of Wheat in the Context of Chinese Land Fallow and Food Security Policies? Findings from Spatio-temporal Changes in Area and Production Between 1990 and 2014

One of the aims of the recently initiated land fallow policy is to encourage winter wheat abandonment in order to recover the groundwater environment of the North China Plain (NCP);although this also threatens a national secure supply of this crop,as the NCP is the major wheat producing area in China.It is therefore necessary to consider regional wheat reallocation in order to meet the twin challenges of production and water conservation.An evaluation of spatiotemporal changes in wheat area and production across China in recent years may shed light on the regions that have the potential for reallocation;such trends are analyzed in this study using agricultural statistical data.Three over-arching principles are proposed that reallocation must be naturally suitable,economically feasible,and socially acceptable,and together with the result of the spatiotemporal analysis,two continuous areas are recommended as potentially suitable for wheat reallocation-alongside the Huai River and the cold region of northeastern China.We also present strategies to improve wheat yields as well as policies for farmers,aiming to encourage the reallocation of wheat to the regions highlighted in this study.

Modeling the spatio-temporal changes in land uses and its impacts on ecosystem services in Northeast China over 2000–2050

Land use and its dynamics have attracted considerable scientific attention for their significant ecological and socioeconomic implications.Many studies have investigated the past changes in land use,but efforts exploring the potential changes in land use and implications under future scenarios are still lacking.Here we simulate the future land use changes and their impacts on ecosystem services in Northeast China(NEC) over the period of 2000–2050 using the CLUE–S(Conversion of Land Use and its Effects at Small regional extent) model under the scenarios of ecological security(ESS),food security(FSS) and comprehensive development(CDS).The model was validated against remote sensing data in 2005.Overall,the accuracy of the CLUE–S model was evaluated at 82.5%.Obtained results show that future cropland changes mainly occur in the Songnen Plain and the Liaohe Plain,forest and grassland changes are concentrated in the southern Lesser Khingan Mountains and the western Changbai Mountains,while the Sanjiang Plain will witness major changes of the wetlands.Our results also show that even though CDS is defined based on the goals of the regional development plan,the ecological service value(ESV) under CDS is RMB 2656.18 billion in 2050.The ESV of CDS is lower compared with the other scenarios.Thus,CDS is not an optimum scenario for eco-environmental protection,especially for the wetlands,which should be given higher priority for future development.The issue of coordination is also critical in future development.The results can help to assist structural adjustments for agriculture and to guide policy interventions in NEC.

Dynamic Multi-Graph Spatio-Temporal Graph Traffic Flow Prediction in Bangkok:An Application of a Continuous Convolutional Neural Network

The ability to accurately predict urban traffic flows is crucial for optimising city operations.Consequently,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility patterns.Deep learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal dependencies.However,these models often become overly complex due to the large number of hyper-parameters involved.In this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction tasks.The comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest accuracy.On the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 min.Similarly,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer periods.The Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time intervals.These numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.