Geospatial Method Research Articles

COVID-19 contact tracking based on person reidentification and geospatial data

Efficient contact tracing is a crucial step in preventing the spread of COVID-19. However, the current methods rely heavily on manual investigation and truthful reporting by high-risk individuals. Mobile applications and Bluetooth-based contact tracing methods have also been adopted, but privacy concerns and reliance on personal data have limited their effectiveness. To address these challenges, in this paper, a geospatial big data method that combines person reidentification and geospatial information for contact tracing is proposed. The proposed real-time person reidentification model can identify individuals across multiple surveillance cameras, and the surveillance data is fused with geographic information and mapped onto a 3D geospatial model to track movement trajectories. After real-world verification, the proposed method achieves a first accuracy rate of 91.56%, a first-five accuracy rate of 97.70%, and a mean average precision of 78.03% with an inference speed of 13 ms per image. Importantly, the proposed method does not rely on personal information, mobile phones, or wearable devices, avoiding the limitations of existing contact tracing schemes and providing significant implications for public health in the post-COVID-19 era.

Fuzzy Geospatial Object-Based Membership Function Downscaling

The area-to-point kriging method (ATPK) is an important technology of downscaling without auxiliary information in remote sensing. However, it uses a constant semivariogram to downscale geospatial variables, which ignores the spatial heterogeneity between the geospatial objects. To deal with this kind of heterogeneity, this study proposes a fuzzy geospatial object-based ATPK method, which mainly consists of three steps: the extraction of fuzzy geospatial objects, the estimation of semivariograms for each object, and the downscaling of each object by ATPK with the corresponding semivariogram. Two groups of membership functions acquired from Worldview-2 and Sentinel-2 are used to test the proposed approach. Six classic downscaling algorithms are compared, and the results of two experiments show a better performance than the classical methods.

Mapping of Phragmites in estuarine wetlands using high-resolution aerial imagery

Phragmites australis is a widespread invasive plant species in the USA that greatly impacts estuarine wetlands by creating dense patches and outcompeting other plants. The invasion of Phragmites into wetland ecosystems is known to decrease biodiversity, destroy the habitat of threatened and endangered bird species, and alter biogeochemistry. While the impact of Phragmites is known, the spatial extent of this species is challenging to document due to its fragmented occurrence. Using high-resolution imagery from the National Agriculture Imagery Program (NAIP) from 2017, we evaluated a geospatial method of mapping the spatial extent of Phragmites across the state of DE. Normalized difference vegetation index (NDVI) and principal component analysis (PCA) bands are generated from the NAIP data and used as inputs in a random forest classifier to achieve a high overall accuracy for the Phragmites classification of around 95%. The classified gridded dataset has a spatial resolution of 1m and documents the spatial distribution of Phragmites throughout the state's estuarine wetlands (around 11%). Such detailed classification could aid in monitoring the spread of this invasive species over space and time and would inform the decision-making process for landscape managers.

Use of Drone Photogrammetry as An Innovative, Competency-Based Architecture Teaching Process

The use of drones is becoming increasingly popular in various fields. In the case of education, initiatives have emerged in which they are included as tools to develop student’s knowledge, and their use is becoming more frequent. This research aims to present a case study in which students used drones in an architecture course at a higher education institution in Mexico. It sought to develop transversal competencies in students, such as digital transformation and cutting-edge technologies by studying spaces using photogrammetry with drones. The results showed that students increased their motivation and were able to perform a more detailed analysis of the architectural space in which they conducted the study. Additionally, they were able to capture and analyze information from architectural study processes more quickly. Aerial photogrammetry is a geospatial data collection method that offers several advantages over other methods. These advantages include higher resolution, wide coverage, flexibility, lower costs, and increased safety. Aerial photogrammetry can capture high-resolution images of large areas of land in a single flight, making it an efficient and adaptable tool for a variety of applications and environments. Additionally, it can be more economical and safer than other methods, as it avoids ground contact and reduces risks to personnel and equipment. This study is considered attractive, as it presents an example of the implementation of emerging technologies in architectural education.

Adding wind power to a wind‐rich grid: Evaluating secondary suitability metrics

AbstractAs the quantity of renewable electricity generation from wind farms increases in a region, the costs associated with integrating it into the broader electricity system also grow. This is primarily due to the need for dispatchable generators that vary power output to compensate for wind farm power variations. Such “balancing services” are an economic cost to the system that is typically not passed on to wind farms. We propose including the use of technical merits other than capacity factor and cost of energy for evaluating new wind farm sites and present a new graphical geospatial method, with the intention of identifying sites that minimize the need for additional electricity balancing service and transmission congestion. Specifically, locations with low correlation to existing wind farms, locations with high correlation to load, locations with high characteristic power time‐shift from existing wind farms, and locations that relieve or do not negatively impact electricity transmission congestion are identified. A geospatial Venn diagram‐based method of visualization is presented. These methods will equip regional planners with new tools to encourage wind farm development in areas that benefit the electricity grid beyond the lowest bid price.

A REVIEW OF METHODS AND REGRESSION MODELS USING SATELLITE IMAGERIES ON PHYTOPLANKTON'S WATER QUALITY PARAMETERS ESTIMATION

Abstract. Water quality monitoring is compulsory to maintain and preserve aquatic ecosystem health, especially for the phytoplankton community. Phytoplankton abundance relies greatly on the condition of water, it is important to assess the water quality parameter (WQP) to estimate the abundance of PP. However, obtaining WQP using conventional methods (water sampling and laboratory assessment) requires more time and cost of operation. Therefore, Geographical Information System (GIS) and remote sensing (RS) approaches are becoming popular methods of measuring water quality parameters (turbidity, total suspended solids (TSS), temperature, pH, etc). This paper aims to review the assessment of WQP in relation to PP abundance and other interchangeable factors from the recent studies and efforts on WQP assessment using geospatial technologies approaches. Methods, algorithms, and accuracies established from the GIS and RS techniques are discussed. From ten (10) extended review research articles, it is revealed that most WQP has an indirect and direct effect on human activities, seasonal changes, fish production, water pollution, and especially PP abundance. In addition, about nine (9) previous research articles revealed the use of various satellite image sensors to estimate WQP from Landsat 8 is the most common, to Landsat 7 ETM+, 5, Sentinel MSI, and the least used is RapidEye. Further research also finds that the three most common types of WQP estimated via the geospatial analysis method are turbidity, pH, and Secchi depth with the highest R2 value equal to 0.810,0.947, and 0.990 respectively.

Representing Spatial Data with Graph Contrastive Learning

Large-scale geospatial data pave the way for geospatial machine learning algorithms, and a good representation is related to whether the machine learning model is effective. Hence, it is a critical task to learn effective feature representation for geospatial data. In this paper, we construct a spatial graph from the locations and propose a geospatial graph contrastive learning method to learn the location representations. Firstly, we propose a skeleton graph in order to preserve the primary structure of the geospatial graph to solve the positioning bias problem of remote sensing. Then, we define a novel mixed node centrality measure and propose four data augmentation methods based on the measure. Finally, we propose a heterogeneous graph attention network to aggregate information from both the structural neighborhood and semantic neighborhood separately. Extensive experiments on both geospatial datasets and non-geospatial datasets are conducted to illustrate that the proposed method outperforms state-of-the-art baselines.

Landfast sea ice break out patterns in the northern Bering Sea observed from C-band Synthetic Aperture Radar

Arctic sea ice is declining in areal extent and seasonal duration, affecting stable landfast sea ice regimes. These landfast ice regimes are vital platforms for local indigenous subsistence hunters and epontic primary production species supporting local and regional food webs. Under changing thermodynamic and mechanical stresses, landfast ice can become more prone to break out events - unexpected mid-season detachments from the coastline. However, the prevalence of break out events in the landfast ice annual cycle on an interannual and decadal basis is generally understudied. Here, we detect and quantify landfast ice break-out events at St. Lawrence Island in the Northern Bering Sea. We accomplished this using C-band Synthetic Aperture Radar (SAR) imagery to detect landfast ice cover. We also advanced a geospatial analysis method to identify break-out events and distinguish such occurrences from end-of-season breakups. Results reveal that 35 break-outs occurred across four sections of the St. Lawrence Island coastline from 1996 − 2019, with 74 % of break-outs occurring on the northern coastlines. Break-outs generally occurred during annual cycles with higher than average landfast ice cover. During the break-out events, maximum temperatures seldom exceed conditions promoting melt, whereas wind speeds are, on average, 2 m/s faster compared to end-of-season breakup events. However, additional datasets are needed to understand better the influence of tidal amplitude and ocean currents on detected break-out occurrence and location. Our study provides the basis for future research to understand break-out events in landfast ice annual cycles at fine spatial scales unavailable in existing sea ice datasets.

The assessment of Groundwater Quality of Confined Aquifer Based on Hydrochemistry in the Alluvial Plain of Semarang City

Water is one of the most important components for living things, including humans. The need for water will increase along with the increase in population in an area. It occurs in urban areas such as Semarang City which is the capital city of Central Java Province with the development of industry, trade and tourism growing rapidly. Rapid development occurred in the alluvial plains of Semarang City. Groundwater is still one of the main sources of water in Semarang City, both unconfined aquifer and confined aquifer. The unconfined aquifer is generally used by the community to meet their needs for bathing and washing via dug wells, while the confined one is developed by the industrial sector and is not least a source of drinking water via deep wells. This study aims to determine the quality of groundwater for drinking water at the study site of the confined aquifer. There are 30 groundwater samples were taken to test the chemical content of groundwater. The method used was the geospatial method and the Water Quality Index (WQI). The spatial method aims to determine the distribution of groundwater quality in the study area. WQI method was to determine the quality of groundwater for drinking water purposes. The results of the hydrochemical analysis showed that groundwater conditions are affected by weathering of silicate minerals present in the lithology of the study site. The weathering of these minerals results in ionic changes in the groundwater. WQI shows 1 sample is included in the poor classification and 2 samples are included in the very poor classification. It locates in the western and central parts of the study location.

Riverine flood vulnerability assessment and zoning using geospatial data and MCDA method in Aq’Qala

Aq’Qala county has been categorized in high flood-prone areas in Iran, therefore it faced many major flood events in last two decades (e.g. in 2001, 2002, 2007, 2012, 2017, and 2019). Forecasting of flood-prone areas would be essential for planning of flood management strategies. Hence the main aim of the current study is to produce and validate flood vulnerability rate (FVR) map relying on geospatial data. Vulnerability criteria were identified through flood expert's consultations, field surveys and taking into consideration a flood event of 2019. Subsequently, the criteria clustered into five main classes: topography, climatology, human factors, geology and morphology. All sub-criteria were analysed using an analytical hierarchy process (AHP) questionnaire and fuzzification by triangular fuzzy number (TFN-AHP) in order to weighting. The FVR maps indicated that 26.1% (AHP map) to 29.66% (TFN-AHP map) of Aq’Qala have been located in very-high vulnerability rate. The least difference between AHP and TFN-AHP were 12.99% and 17.41% in very-high and high vulnerability rates, respectively. Moreover the least difference between the FVR maps and remote sensing flood mapping were 6.55% (AHP) and 2.33% (TFN-AHP). Base on time series satellite images-derived there was high compatibility between TFN-AHP map and flooding map of 2019 flood event. Results demonstrated that application of remote sensing data and Multi-Criteria methods simultaneously can provide reliable outputs.

Investigating Population Exposure Assignment Methods for Air Pollution from Google Street View Polyline Data in Copenhagen, Denmark

BACKGROUND AND AIM: Google Street View (GSV) cars provide air pollution (AP) data across thousands of streets in multiple cities. Various methods exist for linkage of such vector data with populations. While rasterization or near-analysis are possible methods, multiple streets often surround residences; thus, a composite value can be assigned for geo-locations. We aimed to identify best geospatial method for exposure assignment from such data. METHODS: Long-term mean AP [ultra-fine particles (UFP), nitrogen dioxide (NO2), and black carbon (BC)] predictions across 30,312 streets (length = 15-60 m) were obtained from GSV-based mixed-effects LUR models developed for Copenhagen, Denmark. A near-analysis was used where Euclidean distances between each residence (out of ~77,000) and surrounding streets were calculated, nearest street was identified, and its AP values were assigned. Predictions were also assigned to mid-street centroid; using a systematic algorithm data were split to train (24,061; ~80%) and test sets (3,031; ~10%). Spatial averaging (SA), inverse distance weighting (IDW), ordinary kriging (OK), and natural neighbor (NN) models with multiple configurations for weighting and cell-size were developed. The coefficient of determination (R2) and RMSE were calculated on the test sets. RESULTS: The mean (SD) of UFP, NO2, and BC were, respectively, 14,120 (8,849) particles/cm³, 16.8 (8.3) μg/m³, and 1.1 (0.4) μg/m³. Overall, 9 SA, 27 IDW, 45 OK, and 3 NN models were developed. NN with a cell-size of 15m was the best performing model. The R2 and RMSE for NN on the test sets were, respectively, 0.92 and 2543 pt/cm3 for UFP, 0.87 and 3.1 µg/m3 for NO2, and 0.88 and 0.15 µg/m3 for BC. The Spearman correlation between residential predictions from NN and near-analysis assignment method was 0.97 for UFP, 0.95 for NO2, and 0.93 for BC. CONCLUSIONS: Although high correlation was observed for NN and near-analysis, the latter overestimated the concentrations.

Geospatial Analysis of Organ Transplant Referral Regions

System and center-level interventions to improve health equity in organ transplantation benefit from robust characterization of the referral population served by each transplant center. Transplant referral regions (TRRs) define geographic catchment areas for transplant centers in the US, but accurately characterizing the demographics of populations within TRRs using US Census data poses a challenge. To compare 2 methods of linking US Census data with TRRs-a geospatial intersection method and a zip code cross-reference method. This cohort study compared spatial congruence of spatial intersection and zip code cross-reference methods of characterizing TRRs at the census block level. Data included adults aged 18 years and older on the waiting list for kidney transplant from 2008 through 2018. End-stage kidney disease. Multiple assignments, where a census tract or block group crossed the boundary between 2 hospital referral regions and was assigned to multiple different TRRs; misassigned area, the portion of census tracts or block groups assigned to a TRR using either method but fall outside of the TRR boundary. In total, 102 TRRs were defined for 238 transplant centers. The zip code cross-reference method resulted in 4627 multiple-assigned census block groups (representing 18% of US land area assigned to TRRs), while the spatial intersection method eliminated this problem. Furthermore, the spatial method resulted in a mean and median reduction in misassigned area of 65% and 83% across all TRRs, respectively, compared with the zip code cross-reference method. In this study, characterizing populations within TRRs with census block groups provided high spatial resolution, complete coverage of the country, and balanced population counts. A spatial intersection approach avoided errors due to duplicative and incorrect assignments, and allowed more detailed and accurate characterization of the sociodemographics of populations within TRRs; this approach can enrich transplant center knowledge of local referral populations, assist researchers in understanding how social determinants of health may factor into access to transplant, and inform interventions to improve heath equity.

Assessing Groundwater Dynamics and Potentiality in the Lower Ganga Plain, India

The present study intended to assess groundwater storage dynamics (GWS) and identify potential zones using the Multi-Criteria Decision Making (MCDM) method and geospatial technology in the Murshidabad district of West Bengal, India. The study district is located in the Ganga–Padma–Bhagirathi rivers’ floodplain and covers approximately a 5324 km2 area, comprising 26 blocks in five sub-divisions. The study portrayed a quantitative investigation of the pre-monsoon and post-monsoon season’s variability of GWS from 2000 to 2020, taking Landsat TM/Landsat 8 OLI/SRTM satellite data. The geo-spatio-temporal analysis of groundwater storage variability for 20 years was carried out by such remotely sensed data with the geospatial method to portray the dynamics and uncover the potential zones of GWS using various cartographic and statistical techniques. We determined nine parameters for the study, and the analytical hierarchy process (AHP) method was employed for the computation. The present estimation and assessment include the MCDM method, covering assorted parameters and the variations and aspects of GWS in the pre- and post-monsoon seasons from 2000 to 2020. The outcome illustrates that a decline in water storage has taken place in most of the blocks of Murshidabad district on average during the study period, which indicates a water stress provison in the near future. However, the micro (block)-level scenario of the spatiotemporal dynamics of GWS and the potential zonation in the Murshidabad District were investigated to form a location-specific micro-level arrangement for the sustainable management of water.

An analysis of multidimensional poverty in Nigeria using statistical and geospatial modelling: A case study of Jigawa state

Despite recent advances in reducing poverty across the world, millions of people remain on the verge of or already living in severe multidimensional poverty especially in third world nations. The poor in Nigeria suffer from a feeling of voicelessness, helplessness, mistreatment, a complete lack of capacity to influence important choices that impact their life, and a lack of social networking inside state and societal organisations. The goal of this research is to conduct a geospatial analysis of Nigeria’s multidimensional poverty and to identify the geospatial distribution pattern of poverty in Jigawa State as a case study. As a result, comprehend the causes of Jigawa’s complicated poverty condition and to create the state’s first ever poverty map. Also, to look at the country’s poverty trends, with a particular emphasis on Jigawa. The National Bureau of Statistics provided the headcount poverty statistics for Nigerian states, which were downloaded and analysed using simple geospatial approach. The findings revealed a dynamic pattern in Nigerian state poverty from 1996 to 2019. The distribution of poverty in Jigawa state, as a case study, revealed that physical and natural environment resources play a critical role in the state’s high poverty rate. Natural drainage, fertile soil, flat topography, and vegetation pattern all aid other people’s poverty levels in different parts of the state. Future study will examine the linking between environmental, social, religious, and political factors and multidimensional poverty using a geospatial method to map the state’s poverty, which has consistently ranked at the bottom of the Nigeria States Poverty Index.

Synergistic data fusion of satellite observations and in-situ measurements for hourly PM2.5 estimation based on hierarchical geospatial long short-term memory

PM2.5 as a primary air pollutant has adverse effects on the environment and public health. The air quality monitoring stations are distributed sparsely and unevenly, making it difficult to provide continuous and precise regional measurements, which can be supplemented by satellite observations. However, most satellite-based approaches for air pollution estimation are difficult to extract the spatio-temporal dependencies effectively, leading to lower accuracy in long-term prediction and assessment of episodic changes. To fill this gap, a hierarchical geospatial long short-term memory method (HG-LSTM) by considering the geospatial autocorrelation was proposed for hourly PM2.5 estimation with 2-km spatial resolution in Yangtze River Delta (YRD) urban agglomeration. The superior accuracy of the HG-LSTM is compared with other models via the site-based and year-based cross-validation (CV) tests, indicating geospatial autocorrelation exerts non-negligible impacts on the PM2.5 estimation. The estimations are consistent with the in-situ observations with site-based CV R2 of 0.88. The deviations less than 10 μ g/m3 account for over 80%. The PM2.5 spatiotemporal characteristics in the YRD reveal that PM2.5 concentrations are higher in the morning and decline significantly in the afternoon. As well, elevated PM2.5 values are accumulated in the northern regions of the study area. Although the prediction accuracy decreases as the augment of prediction timesteps, the results can still be useful to detect air pollution changes in the near future. Overall, the HG-LSTM model can estimate hourly PM2.5 concentrations accurately and seamlessly, which is beneficial for air pollution monitoring and environmental protection strategy formation.

Spatially autocorrelated training and validation samples inflate performance assessment of convolutional neural networks

Deep learning and particularly Convolutional Neural Networks (CNN) in concert with remote sensing are becoming standard analytical tools in the geosciences. A series of studies has presented the seemingly outstanding performance of CNN for predictive modelling. However, the predictive performance of such models is commonly estimated using random cross-validation, which does not account for spatial autocorrelation between training and validation data. Independent of the analytical method, such spatial dependence will inevitably inflate the estimated model performance. This problem is ignored in most CNN-related studies and suggests a flaw in their validation procedure. Here, we demonstrate how neglecting spatial autocorrelation during cross-validation leads to an optimistic model performance assessment, using the example of a tree species segmentation problem in multiple, spatially distributed drone image acquisitions. We evaluated CNN-based predictions with test data sampled from 1) randomly sampled hold-outs and 2) spatially blocked hold-outs. Assuming that a block cross-validation provides a realistic model performance, a validation with randomly sampled holdouts overestimated the model performance by up to 28%. Smaller training sample size increased this optimism. Spatial autocorrelation among observations was significantly higher within than between different remote sensing acquisitions. Thus, model performance should be tested with spatial cross-validation strategies and multiple independent remote sensing acquisitions. Otherwise, the estimated performance of any geospatial deep learning method is likely to be overestimated.

Comparing and Analysis of Geospatial Interpolation Prediction Algorithm: Case Study The Quality of Education of Malang and Batu City, Indonesia

Abstract. The number of schools in Indonesia continues to grow. This must also be balanced with improving the quality of education in accordance with the objectives of the 4 SDGs, which as a whole are to improve the quality of education that is inclusive, equitable and provides lifelong learning opportunities. However, until now it is very difficult to determine differences in the quality of education in an area. From the problem of education quality and education equity, it is necessary to have a regional analysis of the quality of education. This analysis can be performed using various geospatial interpolation methods. Geospatial Interpolation is a technique to find the value of a missing variable in a known data range in an area. The data used for the Geospatial interpolation process in this study are School Quality data taken through research questionnaires, as well as school accreditation data at the junior high school level. The geospatial interpolation method used in this study is the Inverse Distance Weighted, Spline, Kriging and Natural Neighbor methods. The use of different interpolation methods can indicate the best method for this research case study. Measurement validation results from each geospatial interpolation method using RMSE. From the results of this accuracy validation, the most accurate method will be obtained in determining the quality of education contained in an area.

Impacts of the choice of distance measurement method on estimates of access to point-based resources.

Lack of access to resources such as medical facilities and grocery stores is related to poor health outcomes and inequities, particularly in an environmental justice framework. There can be substantial differences in quantifying "access" to such resources, depending on the geospatial method used to generate distance estimates. We compared three methods for calculating distance to the nearest grocery store to illustrate differential access at the census block-group level in the Atlanta metropolitan area, including: Euclidean distance estimation, service areas incorporating roadways and other factors, and cost distance for every point on the map. We found notable differences in access across the three estimation techniques, implying a high potential for exposure misclassification by estimation method. There was a lack of nuanced exposure in the highest- and lowest-access areas using the Euclidean distance method. We found an Intraclass Correlation Coefficient (ICC) of 0.69 (0.65, 0.73), indicating moderate agreement between estimation methods. As compared with Euclidean distance, service areas and cost distance may represent a more meaningful characterization of "access" to resources. Each method has tradeoffs in computational resources required versus potential improvement in exposure classification. Careful consideration of the method used for determining "access" will reduce subsequent misclassifications.

MACHINE LEARNING APPROACH FOR TENAGA NASIONAL BERHAD (TNB) OVERHEAD POWERLINE AND ELECTRICITY POLE INVENTORY USING MOBILE LASER SCANNING DATA

Abstract. Electricity assets recognition and inventory is a fundamental task in the geospatial-based electrical power distribution management. In Malaysia, Tenaga Nasional Berhad (TNB) aims to complete their assets inventory throughout the country by 2022. Previous research has shown that a method for assets detection especially for TNB is still at an early stage, which mainly relied on manual extraction of the assets from different data sources including mobile laser scanner (MLS). This research aims at evaluating a geospatial method based on machine learning to classify the TNB assets using high density MLS data. The MLS data was collected using Riegl VMQ-1 HA scanner and supported by the base station and control points for point cloud registration purpose. In the first stage the point clouds were classified into ground and non-ground objects. The non-ground points were further classified into different landcover types i.e. vegetation, building, and other classes. The points classified as other classes were used for overhead powerline and electricity poles classification using random forest-based Machine Learning (ML) approach in LiDAR 360 software. Based on the classified point clouds, detailed characteristics of electricity poles (i.e. number of poles, height, diameter and inclination from ground) and overhead powerlines (number of cable segments) were estimated. This information was validated using field collected reference data. The results show that the detection accuracy for electricity poles and overhead power line are 65% and 63% respectively. The estimation of length, diameter and height of the spun pole from point clouds has produced Root Mean Square Error (RMSE) value of 0.081cm, 0.263 cm and 0.372 cm respectively. Meanwhile for the concrete pole, the length, diameter and height has been successfully estimated with the value of RMSE of 0.034 cm, 0.029 cm and 0.331 cm respectively. The length of overhead powerline was estimated with 59.02 cm RMSE. In conclusion, the MLS data had show promising results for a semi-automatic detection and characterization of TNB overhead powerlines and poles in the sub-urban area. Such outcome can be used to support the inventory and maintenance process of the TNB assets.

A new method to map groundwater-dependent ecosystem zones in semi-arid environments: A case study in Chile

Groundwater (GW) use has intensified in recent decades, threatening the ecological integrity of groundwater-dependent ecosystems (GDEs). The study of GDEs is limited; therefore, integrated, interdisciplinary environmental approaches that guarantee their monitoring and management amid current climate and anthropogenic changes are needed. A new geospatial method with an integrated and temporal approach was developed through a multicriteria approximation, taking into account expert opinion, remote sensing-GIS, and fieldwork to map groundwater-dependent ecosystem zones (GDEZ). A survey of experts (N = 26) was conducted to assign degrees of importance to the various geospatial parameters, and the mapping was carried out using 14 parameters. The reclassified parameters were normalized on a scale of 1 to 5 according to the degree of probability of the presence of GDE. The validation was carried out through fieldwork and statistical analysis. Then, the spatio-temporal changes amid changing GW levels were assessed using the summer season normalized difference vegetation index (NDVI). Two GDEZ maps were obtained, for 2002 and 2017, between which the high- and very-high-probability zones of GDEs decreased by 31,887 ha (~ 38%). The most sensitive temporal parameters that most influenced the spatio-temporal changes on GDEs were precipitation and land use, with rain exerting a slightly the greatest influence. It was also demonstrated that identified ecosystems decreased in area or were affected by aquifer depletion (NDVI-GW, r Pearson ≥0.74). This validated method allows spatio-temporal changes in GDEs to be mapped and analyzed at an annual scale and is transferable to other arid and semi-arid environments.