Geographically Weighted Principal Component Analysis Research Articles

Assessing heat vulnerability in Philadelphia using geographically weighted principal component analysis (GWPCA): A geospatial big data-driven approach

The impact of climate change, specifically more intense heat waves, has increased concerns about heat vulnerability, particularly among high-risk populations. This research utilizes multi-source geospatial big data and employs Geographically Weighted Principal Component Analysis (GWPCA) as well as Global Principal Component Analysis (GPCA) to analyze heat vulnerability in Philadelphia. Using GPCA, four key components are identified Sensitivity, Adaptive Capacity, proxy for Sensitivity, and Exposure, respectively. The subsequent GWPCA analysis reveals localized vulnerability differences, showing distinct patterns across the city. Notably, Sensitivity factors are prominent in the western and southwestern regions, whereas Exposure is dominant in the central and southern parts. This study underscores the significance of considering spatial heterogeneity when assessing heat vulnerability. It also highlights the potential of GWPCA to capture subtle disparities within specific areas and proposes targeted strategies to reduce heat vulnerability in affected communities. Therefore, the incorporation of an advanced spatial analysis model enables a comprehensive understanding of heat vulnerability in complex urban environments. This progress is crucial in enhancing resilience and adaptation to evolving climate conditions.

A spatial indicator of environmental and climatic vulnerability in Rome

BackgroundUrban areas are disproportionately affected by multiple pressures from overbuilding, traffic, air pollution, and heat waves that often interact and are interconnected in producing health effects. A new synthetic tool to summarize environmental and climatic vulnerability has been introduced for the city of Rome, Italy, to provide the basis for environmental and health policies. MethodsFrom a literature overview and based on the availability of data, several macro-dimensions were identified on 1,461 grid cells with a width of 1 km2 in Rome: land use, roads and traffic-related exposure, green space data, soil sealing, air pollution (PM2.5, PM10, NO2, C6H6, SO2), urban heat island intensity. The Geographically Weighted Principal Component Analysis (GWPCA) method was performed to produce a composite spatial indicator to describe and interpret each spatial feature by integrating all environmental dimensions. The method of natural breaks was used to define the risk classes. A bivariate map of environmental and social vulnerability was described. ResultsThe first three components explained most of the variation in the data structure with an average of 78.2% of the total percentage of variance (PTV) explained by the GWPCA, with air pollution and soil sealing contributing most in the first component; green space in the second component; road and traffic density and SO2 in the third component. 56% of the population lives in areas with high or very high levels of environmental and climatic vulnerability, showing a periphery-centre trend, inverse to the deprivation index. ConclusionsA new environmental and climatic vulnerability indicator for the city of Rome was able to identify the areas and population at risk in the city, and can be integrated with other vulnerability dimensions, such as social deprivation, providing the basis for risk stratification of the population and for the design of policies to address environmental, climatic and social injustice.

Calculation of the Risk Index for Diarrhea, ISPA, and Pneumonia in Toddlers in the City of Bandung Using Geographically Weighted Principal Component Analysis

Diarrhea, ISPA, and pneumonia are infectious diseases that are prone to occur in toddlers. The management of these three diseases is included in the Republic of Indonesia Ministry of Health's National Priorities for 2020-2024. One area that has a high risk of diarrhea, ARI, and pneumonia in toddlers is the city of Bandung. Effective and efficient disease control is needed, namely by controlling the three diseases simultaneously which can be emphasized on improving environmental quality, especially in areas with high disease risk. The analysis found that there is a spatial dependence on each variable and each variable is correlated with one another. Therefore, in this study used Geographically Weighted Principal Component Analysis (GWPCA). Calculation of the risk index and mapping with GWPCA produces a combined risk index of the three observed diseases by considering the spatial dependence of the data.

Identification and analysis of transitional zone patterns along urban-rural-natural landscape gradients: An application to China’s southwest mountains

Urban-rural-natural (U-R-N) gradients can integrate numerous landscapes with distinct regional functions to illustrate the uncertainty, dynamics, and gradients of the mountainous socio-ecological systems. Hence, identifying transitional zones (TZs) along U-R-N landscape gradients, which contain cohesively various landscapes, and analyzing their transition trends and patterns are of paramount significance for regional landscape planning. Through the integration of geographically weighted principal component analysis (GWPCA), raster rearrangement, and abrupt bin detection, this study aims to develop a novel framework approach for identifying TZs and analyzing transition trends and type patterns along U-R-N gradients in southwestern mountains, China. The findings indicate that TZs cover 61,880 km2 and account for 5.37 % of southwestern mountains, primarily in the hills and mountains of the Sichuan Basin and the Yunnan-Guizhou Plateau. TZs are typically found along U-R-N gradients; however, they are most concentrated in the R1 and R2 of rural landscapes, with farmlands being the most extensively distributed land use type inside TZs. In the southwest mountains, the TZs patterns along U-R-N gradients cover 9 landscape types, including 4 TZ types, of which urban-rural transition zones (U-RTZ) account for 49.36 % of all TZs and comprise the most complete U-R-N gradients. Gradients may also be detected in the component structures of TZs, and TZs have become increasingly sharp and prominent along U-R-N and topographical gradients. This framework approach overcomes the restrictions of previous TZs that were limited to nearby geographical boundaries, and can contribute to our understanding the mutual feedbacks and interactive processes of mountainous coupled socioecological systems, thus empowering the provision of a more elastic space for revolutionary growth while still protecting variegated natural habitats in mountains for future generations.

Spatiotemporal Change in Livestock Population and Its Correlation with Meteorological Disasters during 2000–2020 across Inner Mongolia

Inner Mongolia (IM) is one of the five major pastoral areas in China, and animal husbandry is its traditional industry. The population of livestock is an important factor affecting the sustainable development of livestock and grassland. Due to the special geographical location of IM, various meteorological disasters occur frequently, which have a significant impact on the local livestock population. In this study, principal component analysis (PCA) and geographically weighted principal component analysis (GWPCA) were used to explore the spatial and temporal patterns of small livestock and large livestock populations in county-level administrative units from 2000 to 2020, and the effects of meteorological disasters on livestock populations were also considered. We found that the cumulative proportion of total variance (CPTV) of the first two principal components of global PCA for small livestock and the first principal component for large livestock reached 94.54% and 91.98%, respectively, while the CPTV of GWPCA was in the range of 93.23–96.45% and 88.47–92.49%, respectively, which showed stronger spatial explanation; the small livestock population was significantly correlated with spring drought, summer drought, spring–summer drought and snow disaster. However, the correlation between large livestock and summer drought and spring–summer drought is greater. We conclude that GWPCA can better explain the spatial change of livestock populations; meteorological disasters have both advantages and disadvantages on the livestock population, and the drought types that have a greater impact on livestock are summer drought and spring–summer drought. There are geographical differences in the impact of meteorological disasters, with drought affecting most of IM and snow disaster mainly affecting the eastern region; large livestock were mainly affected by drought, while small livestock were affected by both drought and snow disaster.

Urban environmental vulnerability in Rome: a spatial composite indicator

BACKGROUND AND AIM: In recent decades, in order to respond to the growing need for systematic information on complex realities, there have been increasing attempts to create synthetic and complex indicators, in many areas of knowledge, capable to integrate a large amount of information. The aim of this paper is summed the environmental dimension in a synthetic index able to inform on the urban risk in one of the largest cities in Europe, Rome, Italy. METHODS: Rome is characterized by a complex landscape with various anthropogenic and natural source of pollutions. To analyses different landscape components and tries to make a synthesis 1km2 grid cells were fixed as the reference unit for all spatial predictor indicators. Variables include several aims: Anthropic Industrial pressure; Airport; Land cover data; Road data defined as road density and traffic intensity and noise; Green area, ndvi and lai; hydrogeologic risk; environmental pollution; temperature; socioeconomic status. The Geographically Weighted Principal Component Analysis (GWPCA) method was used to construct a composite indicator by integrating all the dimensions. RESULTS: The first four components are used to explain the most variation in the data structure. The total percentage of variance (PTV) explained ranges from 78% to 85% with an average value of 82%. The overall value of the urban vulnerability composite indicator evidence the spatial variability of the landscape. Sign with high level the major urbanization areas and the main industrial sites of the city, detects also a gradient between the most populated areas and the green areas. CONCLUSIONS: A spatial principal component analysis will be performed to integrate several indicators. Synthesis has the advantage of avoiding the presentation and interpretation of a large number of elementary indicators in order to perform simpler and faster analyses, especially in comparative terms. KEYWORDS: Geographically Weighted Principal Component Analysis, composite indicator

Comparing Global and Spatial Composite Measures of Neighborhood Socioeconomic Status Across US Counties.

Area-level neighborhood socioeconomic status (NSES) is often measured without consideration of spatial autocorrelation and variation. In this paper, we compared a non-spatial NSES measure to a spatial NSES measure for counties in the USA using principal component analysis and geographically weighted principal component analysis (GWPCA), respectively. We assessed spatial variation in the loadings using a Monte Carlo randomization test. The results indicated that there was statistically significant variation (p = 0.004) in the loadings of the spatial index. The variability of the census variables explained by the spatial index ranged from 60 to 90%. We found that the first geographically weighted principal component explained the most variability in the census variables in counties in the Northeast and the West, and the least variability in counties in the Midwest. We also tested the two measures by assessing the associations with county-level diabetes prevalence using data from the CDC's US Diabetes Surveillance System. While associations of the two NSES measures with diabetes did not differ for this application, the descriptive results suggest that it might be important to consider a spatial index over a global index when constructing national county measures of NSES. The spatial approach may be useful in identifying what factors drive the socioeconomic status of a county and how they vary across counties. Furthermore, we offer suggestions on how a GWPCA-based NSES index may be replicated for smaller geographic scopes.

Geographically and temporally weighted principal component analysis: a new approach for exploring air pollution non-stationarity in China, 2015–2019

ABSTRACT In spatiotemporal applications, geographically weighted principal component analysis (GWPCA) is commonly adopted to describe spatial heterogeneity. However, time effects are ignored in GWPCA. In this study, the temporal effect was incorporated into GWPCA . Thus, an extended model, geographically and temporally weighted principal component analysis (GTWPCA), was developed to simultaneously explore spatial and temporal non-stationarity. The GTWPCA was implemented using a case study of air pollution in China. The results mainly show that GTWPC1 (the local component one in GTWPCA) corresponds to a ‘winning group’ with constantly varying ‘winning’ variables adapted to the spatiotemporal non-stationary characteristics of air pollution in China.

Geographically weighted principal component analysis for characterising the spatial heterogeneity and connectivity of soil heavy metals in Kumasi, Ghana

The use of principal component analysis (PCA) for soil heavy metals characterization provides useful information for decision making and policies regarding the potential sources of soil contamination. However, the concentration of heavy metal pollutants is spatially heterogeneous. Accounting for such spatial heterogeneity in soil heavy metal pollutants will improve our understanding with respect to the distribution of the most influential soil heavy metal pollutants. In this study, geographically weighted principal component analysis (GWPCA) was used to describe the spatial heterogeneity and connectivity of soil heavy metals in Kumasi, Ghana. The results from the conventional PCA revealed that three principal components cumulatively accounted for 86% of the total variation in the soil heavy metals in the study area. These components were largely dominated by Fe and Zn. The results from the GWPCA showed that the soil heavy metals are spatially heterogeneous and that the use of PCA disregards this considerable variation. This spatial heterogeneity was confirmed by the spatial maps constructed from the geographically weighted correlations among the variables. After accounting for the spatial heterogeneity, the proportion of variance explained by the three geographically weighted principal components ranged between 85% and 89%. The first three identified GWPC were largely dominated by Fe, Zn and As, respectively. The location of the study area where these variables are dominated provides information for remediation.

Soil fertility quality assessment based on geographically weighted principal component analysis (GWPCA) in large-scale areas

Principal component analysis (PCA) has been widely used in the integrated soil fertility quality index (SFQI) (SFQIPCA) assessment. However, the traditional PCA, only established in variable space, does not consider the spatially varying relationships among soil fertility indicators in large-scale areas, and thus cannot appropriately determine the spatially varying relative importance (i.e., weight calculated based on communality) of soil indicators in the SFQI assessment. Moreover, uncertainty inevitably exists in the spatial distribution pattern of SFQI due to the limited sample points, which is critical to the precision management of soil fertility. To address these limitations, this study first proposed a novel assessment method for SFQI based on geographically weighted principal component analysis (GWPCA) (SFQIGWPCA). Secondly, SFQIGWPCA was assessed in Shayang County, China, and then compared with the traditional SFQIPCA. Finally, the spatial uncertainty of SFQIGWPCA was assessed based on the 1000 realizations generated by sequential Gaussian simulation (SGS). Results showed that (i) spatially varying relationships among soil indicators were revealed by Monte Carlo test and GWPCA outputs (i.e., the winning variable and the local percentage of total variation), while traditionally-used PCA was conducted in the assumption of spatially stationary relationships among soil indicators; (ii) in SFQI assessment, the spatially varying indicator weights were determined by GWPCA, but could not be determined by PCA; (iii) the areas with higher threshold-exceeding probability (≥ 0.95) mainly located in the northwest of this county, and the areas with lower threshold-exceeding probability (≤ 0.05) mainly located in the east of this county. It is concluded that GWPCA adequately considers the spatially varying relationships among soil indicators, and SFQIGWPCA is an effective tool in the SFQI assessment in large-scale areas.

Living environment matters: Unravelling the spatial clustering of COVID-19 hotspots in Kolkata megacity, India

The emergence of COVID-19 has brought a serious global public health threats especially for most of the cities across the world even in India more than 50 % of the total cases were reported from large ten cities. Kolkata Megacity became one of the major COVID-19 hotspot cities in India. Living environment deprivation is one of the significant risk factor of infectious diseases transmissions like COVID-19. The paper aims to examine the impact of living environment deprivation on COVID-19 hotspot in Kolkata megacity. COVID-19 hotspot maps were prepared using Getis-Ord-Gi* statistic and index of multiple deprivations (IMD) across the wards were assessed using Geographically Weighted Principal Component Analysis (GWPCA).Five count data regression models such as Poisson regression (PR), negative binomial regression (NBR), hurdle regression (HR), zero-inflated Poisson regression (ZIPR), and zero-inflated negative binomial regression (ZINBR) were used to understand the impact of living environment deprivation on COVID-19 hotspot in Kolkata megacity. The findings of the study revealed that living environment deprivation was an important determinant of spatial clustering of COVID-19 hotspots in Kolkata megacity and zero-inflated negative binomial regression (ZINBR) better explains this relationship with highest variations (adj. R2: 71.3 %) and lowest BIC and AIC as compared to the others.

Assessing multiscale visual appearance characteristics of neighbourhoods using geographically weighted principal component analysis in Shenzhen, China

The neighbourhood is a basic residential unit and is characterized by its physical setting, functional attributes and visual appearance. The visual appearance of a neighbourhood can directly affect the impression of humans regarding the local living environment. Assessing the characteristics of the visual appearance of a neighbourhood is significance for promoting people's physical activities, improving residents' sense of comfort and even ensuring the equality of facilities. However, studies assessing the spatial characteristics of visual appearance are still limited. Therefore, this article applies street view images to quantify the visual appearance of neighbourhoods at multiple scales in Shenzhen, China. Then, geographically weighted principal component analysis (GWPCA) is employed to explore the varying multivariate structures of visual appearance. The results confirm that GWPCA can be effective in assessing the visual appearance characteristics of neighbourhoods while considering spatial heterogeneity. The visual appearance characteristics of neighbourhoods are sensitive to both the spatial location and analysis scale. The extracted geographically weighted principal components (GWPCs) can represent the original screen elements by emphasizing certain comprehensive concepts, such as walkability, accessibility and vibrancy. The exploratory findings of this article allow for an improvement of studies on spatial quality at the human scale and could potentially guide neighbourhood planning and street design.

Formulation of deprivation index for identification of regional pattern of deprivation in rural India

Deprivation of socio-economic well-being is one of the major reasons behind the occurrence of regional disparity in India. The present study has attempted to present and compare the regional pattern of deprivation in rural India by formulating a simple summary index of multidimensional deprivation (IMD) at the district level using global principal component analysis (PCA) and a Geographically Weighted Principal Component Analysis (GWPCA). The results of the study show that the east-central heartland of India is the most deprived region. On the contrary, the north and south India are in a much better position compared to the other part of the country. The results of the spatial autocorrelation of multidimensional deprivation (Global Moran's I = 0.748) indicates that there is a statistically significant pattern of spatial clustering that includes four distinct categories (High-High, Low-Low, High-Low, and Low-High). The LISA map shows that 151 districts belong to High-High (deprivation hotspots) and 108 districts come under the Low-Low cluster (deprivation cold spots). High-High cluster group spreads along with the ecologically sensitive areas like the Bastar region, Tarai tract, Chotonagpur region, and Dandakaranya region which are dominated by tribal populations.

Data-driven regionalization for analyzing the spatiotemporal characteristic of air quality in China

Abstract. With the development of urbanization and industrialization, the degradation of ambient air quality has become a serious issue that impacts human health and the environment; thus, it has attracted more attention from scholars. Usually, the mass concentrations of sulfur dioxide (SO2), nitrogen dioxide (NO2), carbon monoxide (CO), ozone (O3) and particulate matter with an aerodynamic diameter less than 10 μm and 2.5 μm (PM10 and PM2.5) are used to evaluate air quality. A commonly used data-driven regionalization framework for studying air quality issues, identifying areas with similar air pollution behavior and locating emission sources involves an incorporation of the principal component analysis (PCA) with cluster analysis (CA) methods. However, the traditional PCA does not consider spatial variations, which is a notable issue in geographic studies. This article focuses on extracting the local principal components (PCs) of air quality indicators based on a geographically weighted principal component analysis (GWPCA), which is superior to the PCA when considering spatial heterogeneity. Then, a spatial cluster analysis (SCA) is used to identify the areas with similar air pollution behavior based on the results of the GWPCA. The results are all visualized and show that the GWPCA has a higher explanatory ability than the traditional PCA. Our modified framework based on the GWPCA and SCA for assessing air quality can effectively guide environmentalists and geographers in evaluating and improving air quality from a new perspective. Furthermore, the visualization results can be used by city planners and the government for monitoring and managing air pollution. Finally, policy suggestions are recommended for mitigating air pollution via regional collaboration.

THE USE OF A GEOGRAPHICALLY WEIGHTED ANALYSIS OF THE MAIN COMPONENTS FOR AGRO-ECOLOGICAL ZONING OF THE TERRITORY OF UKRAINE

Agro-ecological zoning (AEZ) is one of the most important bases for agricultural developmental planning.In this study we provide the geographically weighted principal component analysis (GWPCA) as analternative method for agro-ecological zoning of a region. GWPCA makes it possible to construct mapsof spatial heterogeneity of data, which are necessary tools for agro-ecological zoning of the territory. Thepotato yield on the territory of 10 regions (206 administrative districts) of Polissya and Forest-steppe zoneswithin Ukraine was selected as the basis for agro-ecological zoning. The global principal componentsanalysis (PCA) allows establishing 3 principal components, which together explain 43.1% of the overallpotato yields variability. Geographically weighted principal components analysis allowed to investigatelocal patterns in the potato yield dynamics and characterized by greater explanatory ability than the totalmodel. The most common method of GWPCA — mapping of the «winning» variables is not suitable fortime series analysis. Therefore, based on the close types of local dynamics established clusters for each ofthe principal component, and was used the mapping of these clusters, instead of displaying «winning»variables. Geographically weighted principal component analysis showed spatial non-stationary of environmentalregimes, which determine the oscillating component of potatoes yield variation over time. Thespaces, within which the structure of ecological interactions remains unchanged, can be considered as thebasis of agro-ecological zoning of the territory.

The Spatially Varying Components of Vulnerability to Energy Poverty

A household’s vulnerability to energy poverty is socially and spatially variable. Efforts to measure energy poverty, however, have focused on narrow, expenditure-based metrics or area-based targeting. These metrics are not spatial per se, because the relative importance of drivers does not vary between neighborhoods to reflect localized challenges. Despite recent advancements in geographically weighted methodologies that have the potential to yield important information about the sociospatial distribution of vulnerability to energy poverty, the phenomenon has not been approached from this perspective. For a case study of England, global principal component analysis (PCA) and local geographically weighted PCA (GWPCA) are applied to a suite of neighborhood-scale vulnerability indicators. The explicit spatiality of this methodological approach addresses a common criticism of vulnerability assessments. The global PCA reaffirms the importance of well-established vulnerabilities, including older age, disability, and energy efficiency. It also demonstrates striking new evidence of vulnerabilities among precarious and transient households that are less well understood and have become starker during austerity. In contrast, rather than providing a single estimate of propensity to energy poverty for neighborhoods based on a national understanding of what drives the condition, the GWPCA identifies a diverse array of vulnerability factors of greatest importance in different locales. These local results destabilize the geographical configurations of an urban–rural and north–south divide that typify understandings of deprivation in this context. The geographically weighted approach therefore draws attention to vulnerabilities often hidden in policymaking, allowing for reflection on the applicability of spatially constituted methodologies to wider social vulnerability assessments. Key Words: energy poverty, geographically weighted PCA, GIS, spatial analysis, vulnerability.

Data-driven regionalization for analyzing the spatiotemporal characteristics of air quality in China

With the development of urbanization and industrialization, the degradation of air quality has become a serious issue that impacts human health and the environment; thus, it has attracted more attention from scholars. At present, the mass concentrations of sulfur dioxide (SO2), nitrogen dioxide (NO2), carbon monoxide (CO), ozone (O3) and particulate matter with an aerodynamic diameter less than 10 μm and 2.5 μm (PM10 and PM2.5) are used to evaluate air quality in China. A commonly used data-driven regionalization framework for studying air quality, identifying areas with similar air pollution behavior and locating emission sources involves an incorporation of the principal component analysis (PCA) with cluster analysis (CA) methods. However, the traditional PCA does not consider spatial heterogeneity, which is a notable issue in geographic studies. This article focuses on extracting the local principal components of air quality indicators based on a geographically weighted principal component analysis (GWPCA) method, which is superior to the PCA with considering spatial heterogeneity. Then, a spatial cluster analysis (SCA) is used to identify the areas with similar air pollution behavior based on the results of the GWPCA. The results are all visualized and show that the GWPCA has a higher explanatory ability than the traditional PCA. Our modified framework based on the GWPCA and SCA for assessing air quality can effectively guide environmentalists and geographers in evaluating and improving air quality from a spatial perspective. Furthermore, the visualization results can be used by city planners and the government for monitoring and managing air pollution. Finally, policy suggestions are recommended for mitigating air pollution via regional collaboration.

Spatial heterogeneity in Spain for senior travel behavior

Travel patterns are becoming more differentiated, influenced by new variables resulting from changes in lifestyle. The relevance of the senior segment for this industry, with the continuous aging population and their economic status, made this segment a very attractive group for the sector, and even more so in a country that is characterized by its aging, such as Spain. Spatial effects are considered a key element to understand this process, but there are only a few studies focusing on cross-cultural influences and the neighborhood context. For this purpose, the technique of geographically weighted principal component analysis (GWPCA) is applied in a novel way for the sector, showing different behavior patterns according to area of origin. The GWPCA is a localized version of the principal component analysis (PCA) used when there is a certain spatial heterogeneity in the structure of a multivariate data set. The results confirmed that GWPCA is an effective statistical methodology to research spatial heterogeneity for travel behavior, with clearly differentiated scenarios for the north, center and south of Spain, where the most determining factors in each case were hygiene and cleanliness, medical coverage and transport facilities.

Urban deprivation in a global south city-a neighborhood scale study of Kolkata, India

Urban deprivation is an epistemic tool to study the geographic concentration of deprivation in different neighborhoods of a city. Studies have long associated with neighborhood research and have viewed it from multiple perspectives. Most of these researches look into ways how other factors affect a neighborhood or how a neighborhood affects other factors, commonly using global statistical measures to make inferences that only give a summation of local variations. However, in tune with Lewis Mumford’ contention, this article proposes a local measure based index of deprivation that not only gives a neighborhood level results but also takes neighboring effects into consideration. Neighboring effects maintain that a locality seldom exists as a discrete entity rather its characteristic is made up as an amalgamation of multiple characteristics of the contiguous localities. Thus, in this study, an Index of deprivation is devised for the municipal wards of Kolkata city using Geographically Weighted Principal Component Analysis (GWPCA) loadings and compared to that devised from Principal Component Analysis (PCA) loadings. It is found that GWPCA accounts effectively for local variations and neighboring effects at the neighborhood scale. However, both the Indices have pinpointed particular wards that are at the extreme end of the urban deprivation scale irrespective of the measure used.

Spatial Variation in Seasonal Water Poverty Index for Laos: An Application of Geographically Weighted Principal Component Analysis

Water poverty, defined as insufficient water of adequate quality to cover basic needs, is an issue that may manifest itself in multiple ways. Extreme seasonal variation in water availability, such as in Laos, located in Monsoon Asia, results in large differences in water poverty conditions between dry and wet seasons. In this study, seasonal Water Poverty Indices (WPI) are developed for 8215 villages in Laos. WPI is a multidimensional composite index integrating five dimensions of water: resource availability, access to safe water, capacity to manage the resource, its use and environmental requirements. Principal Component Analysis (PCA) and Geographically Weighted PCA (GWPCA) were used to examine drivers of water poverty and to derive different weighting schemes. Three major drivers were identified: poverty, commercial/subsistence agriculture and village location. The least water poor areas are located around the capital city and along the Mekong River Valley while the highest water poverty is found in sparsely populated mountainous areas. Wet season WPI is on average more than 12 index points higher than in the dry season, but in some villages monsoon rain does not improve the situation. The results indicate large spatial and temporal differences in WPI within Laos. In analysis of WPI components, a mean–variance scaled PCA is recommended due to its capacity for uncovering processes driving water poverty. Extending to GWPCA is recommended when information on local differences is of interest.