| 1. |
- Guptha, Guru Chythanya, et al.
(författare)
-
Evaluation of an urban drainage system and its resilience using remote sensing and GIS
- 2021
-
Ingår i: Remote Sensing Applications: Society and Environment. - : Elsevier. - 2352-9385. ; 23
-
Tidskriftsartikel (refereegranskat)abstract
- The increasing number of pluvial floods due to extreme climatic events or poor maintenance of the drainage networks urge for assessing the performance of the urban drainage system (UDS). This paper presents a comprehensive evaluation of the UDS of Gurugram City, India. While the limited availability of sub-hourly precipitation and finer resolution geospatial data pose major challenges in the detailed analyses through Storm Water Management Model (SWMM), it was circumvented by utilizing the high-resolution remotely sensed datasets viz., IMERG (half-hourly precipitation data from 2000 to 2019), ALOS PALSAR (Digital Elevation Model) and Sentinel-2 (land use/land cover). Functional failure scenarios (i.e., the combinations of climate change and urbanization) were simulated to assess the impacts on the resilience of the UDS. The modelling results showed that individually, climate change would impose a more serious threat than urbanization, whereas their combinations would significantly hamper the resilience of the UDS. The structural failure (only single link-failure) scenarios were analyzed, and 11 out of 25 conduits were identified to be non-resilient. The study highlights the importance of the readily available remote sensing datasets, which fill the gap of non-availability of ground-based datasets at desirable resolutions, especially in developing countries.
|
|
| 2. |
- Haas, Jan, 1983-, et al.
(författare)
-
Sentinel-1A SAR and sentinel-2A MSI data fusion for urban ecosystem service mapping
- 2017
-
Ingår i: Remote Sensing Applications: Society and Environment. - : Elsevier. - 2352-9385. ; 8, s. 41-53
-
Tidskriftsartikel (refereegranskat)abstract
- The two main objectives of this study are to evaluate the potential use and synergetic effects of ESA Sentinel-1A C-band SAR and Sentinel-2A MSI data for classification and mapping of ecologically important urban and peri-urban space and to introduce spatial characteristics into ecosystem service analyses based on remotely sensed data. Image resolutions between 5 m and 20 m provided by the Sentinel satellites introduce a new relevant spatial scale in-between high and medium resolution data at which not only urban areas but also their important hinterlands can be effectively and efficiently mapped. Sentinel-1/2 data fusion facilitates both the capture of ecologically relevant details while at the same time also enabling large-scale urban analyses that draw surrounding regions into consideration. The combined use of Sentinel-1A SAR in Interferometric Wide Swath mode and simulated Sentinel-2A MSI (APEX) data is being evaluated in a classification of the Zürich metropolitan area, Switzerland. The SAR image was terrain-corrected, speckle-filtered and co-registered to the simulated Sentinel-2 image. After radiometric and spatial resampling, the fused image stack was segmented and classified by SVM. After post-classification, landscape elements were investigated in terms of spatial characteristics and topological relations that are believed to influence ecosystem service supply and demand, i.e. area, contiguity, perimeter-toarearatio and distance. Based on the classification results, ecosystem service supplies and demands accounting for spatial and topological patch characteristics were attributed to 14 land cover classes. The quantification of supply and demand values resulted in a positive ecosystem service budget for Zürich. The spatially adjusted service budgets and the original budgets are similar from a landscape perspective but deviate up to 50% on thepatch level. The introduction of spatial and topological patch characteristics gives a more accurate impression of ecosystem service supply and demands and their distributions, thus enabling more detailed analyses in complexurban surroundings. The method and underlying data are considered suitable for urban land cover and ecosystem service mapping and the introduction of spatial aspects into relative ecosystem service valuation concepts is believed to add another important aspect in currently existing approaches.
|
|
| 3. |
- Hosseiny, Benyamin, et al.
(författare)
-
Urban land use and land cover classification with interpretable machine learning – A case study using Sentinel-2 and auxiliary data
- 2022
-
Ingår i: Remote Sensing Applications: Society and Environment. - : Elsevier BV. - 2352-9385. ; 28
-
Tidskriftsartikel (refereegranskat)abstract
- The European commission launch of the twin Sentinel-2 satellites provides new opportunities for land use and land cover (LULC) classification because of the readily availability of their data and their enhanced spatial, temporal and spectral resolutions. The rapid development of machine learning over the past decade led to data-driven models being at the forefront of high accuracy predictions of the physical world. However, the contribution of the driving variables behind these predictions cannot be explained beyond generalized metrics of overall performance. Here, we compared the performance of three shallow learners (support vector machines, random forest, and extreme gradient boosting) as well as two deep learners (a convolutional neural network and a residual network with 50 layers) in and around the city of Malmö in southern Sweden. Our complete analysis suite involved 141 input features, 85 scenarios, and 8 LULC classes. We explored the interpretability of the five learners using Shapley additive explanations to better understand feature importance at the level of individual LULC classes. The purpose of class-level feature importance was to identify the most parsimonious combination of features that could reasonably map a particular class and enhance overall map accuracy. We showed that not only do overall accuracies increase from shallow (mean = 84.64%) to deep learners (mean = 92.63%) but that the number of explanatory variables required to obtain maximum accuracy decreases along the same gradient. Furthermore, we demonstrated that class-level importance metrics can be successfully identified using Shapley additive explanations in both shallow and deep learners, which allows for a more detailed understanding of variable importance. We show that for certain LULC classes there is a convergence of variable importance across all the algorithms, which helps explain model predictions and aid the selection of more parsimonious models. The use of class-level feature importance metrics is still new in LULC classification, and this study provides important insight into the potential of more nuanced importance metrics.
|
|
| 4. |
- Kadhim Al-lami, Ahmed, et al.
(författare)
-
Using Vegetation Indices for monitoring the spread of Nile Rose plant in the Tigris River within Wasit province, Iraq
- 2021
-
Ingår i: Remote Sensing Applications: Society and Environment. - : Elsevier. - 2352-9385. ; 22
-
Tidskriftsartikel (refereegranskat)abstract
- The Nile rose or water hyacinth (Eichhornia crassipes) is an aquatic species threaten socio-economic and ecological systems, by invading freshwater ecosystems, affecting their productivity and functionality, as well as causing unfixable damage to key hydrological processes. Spectral signature differences can play a common role through using remote identification for these invasive plants, by using hyperspectral data, while many other studies showed that textural and phrenological differences are also can be considered as an effective strategy in this critical problem. New generation sensors like Sentinel 2 and Landsat 8 sensors of recently launched crop with improved sensing characteristics, unlike the previous broadband multispectral sensors has been provided untapped prospective alternatives. New insights were introduced in the detecting, mapping, and monitoring the spread of Nile Rose aquatic plant in the Tigris River at Wasit province in Iraq which has caused damage to fishing nets and make it difficult for fishermen to paddle on the river. Vegetation indices have been used to assess the impacts on major socio-economic activities in the study area. Spectral reflectance of Landsat 8 operational land imager OLI (acquired at 6 Oct 2016) was used to differentiate the spectral signature of the water hyacinth from other plants. These indices recorded the highest reflection of the Nile Rose plant relative to the rest of the plants. The result showed that the green Chlorophyll Index (CL Green) with overall accuracy of 89% which proved that this study has established a promising method for monitoring the invasion of the Nile Rose in the Tigris River to insure the availability of safe drinking water as a main source for the people such as in the study area nearby the part of Tigris River.
|
|
| 5. |
- Mugiraneza, Theodomir, et al.
(författare)
-
Urban land cover dynamics and their impact on ecosystem services in Kigali, Rwanda using multi-temporal Landsat data
- 2019
-
Ingår i: Remote Sensing Applications: Society and Environment. - : Elsevier B.V.. - 2352-9385. ; 13, s. 234-246
-
Tidskriftsartikel (refereegranskat)abstract
- Land cover change monitoring in rapidly urbanizing environments based on spaceborne remotely sensed data and measurable indicators is essential for quantifying and evaluating the spatial patterns of urban landscape change dynamics and for sustainable urban ecosystems management. The objectives of the study are to analyse the spatio-temporal evolution of urbanization patterns of Kigali, Rwanda over the last three decades (from 1984 to 2016) using multi-temporal Landsat data and to assess the associated environmental impact using landscape metrics and ecosystem services. Visible and infrared bands of Landsat images were combined with derived Normalized Difference Vegetation Index (NDVI), Gray Level Co-occurrence Matrix (GLCM) variance texture and digital elevation model (DEM) data for pixel-based classification using a support vector machine (SVM) classifier. Seven land cover classes were derived with an overall accuracy exceeding 87% with Kappa coefficients around 0.8. As most prominent changes, cropland was reduced considerably in favour of built-up areas that increased from 2.13 km2 to 100.17 km2 between 1984 and 2016. During those 32 years, landscape fragmentation could be observed, especially for forest and cropland. The landscape configuration indices demonstrate that in general the land cover pattern remained stable for cropland, but that it was highly changed for built-up areas. Ecosystem services considered include regulating, provisioning and support services. Estimated changes in ecosystem services amount to a loss of 69 million US dollars (USD) as a result of cropland degradation in favour of urban areas and in a gain of 52.5 million USD within urban areas. Multi-temporal remote sensing is found as a cost-effective method for analysis and quantification of urbanization and its effects using landscape metrics and ecosystem services.
|
|
| 6. |
- Nhangumbe, Manuel, et al.
(författare)
-
Supervised and unsupervised machine learning approaches using Sentinel data for flood mapping and damage assessment in Mozambique
- 2023
-
Ingår i: Remote Sensing Applications: Society and Environment. - : Elsevier BV. - 2352-9385. ; 32
-
Tidskriftsartikel (refereegranskat)abstract
- Natural hazards, such as flooding, have been negatively impacting developed and emerging economies alike. The effects of floods are more prominent in countries of the Global South, where large parts of the population and infrastructure are insufficiently protected from natural hazards. From this scope, a lot of effort is required to mitigate these impacts by continuously providing new and more reliable tools to aid in mitigation and preparedness, during or after a flood event. Flood mapping followed by damage assessment plays an important role in all these stages. In this work we investigate a new dataset provided by DrivenData Labs based on Sentinel-1 (S1) imagery (VH, VV imagery and labels) to help map floods in the city of Beira in Mozambique. Exploiting Google Earth Engine (GEE), we deployed supervised and unsupervised machine learning (ML) methods on a dataset comprising imagery from 13 countries worldwide. We first mapped the floods country-by-country including Mozambique. This first part was helpful to understand the sensitivity of each method when applied to data from different regions and with different polarizations. We then trained the supervised model globally (in all 13 countries) and used it to predict floods in Beira. To assess the accuracy of the experiments we used the intersection over the union (IoU) metric, results of which we compared with the benchmark IoU achieved by the winner in the DrivenData competition for flood mapping in 2021. The implementation of unsupervised and supervised ML using VH and VV+VH produced satisfactory results, and showed to be better than using VV imagery; in Cambodia and Bolivia with VH polarization yielded IoUs values ranging from 0.819 to 0.856 which is above the benchmark (0.8094). The predictions in Beira using VH imagery yielded IoU of 0.568, which is a reasonable outcome. The proposed approach is a reliable alternative for flood mapping, especially in Mozambique due to its low cost and time effectiveness as even with unsupervised approaches, relatively high-quality results are yielded in near real-time. Finally, we used Sentinel-2 (S2) imagery for a land cover classification to perform damage assessment in Beira and integrated population data from Beira to enhance the quality the results. The results show that 20% of agricultural area and about 10% of built up area were flooded. Flooded built up area includes highly populated neighborhoods such as Chaimite and Ponta Gea that are located in the center of the city.
|
|
| 7. |
- Njoku, Elijah A., et al.
(författare)
-
Quantitative assessment of the relationship between land use/land cover (LULC), topographic elevation and land surface temperature (LST) in Ilorin, Nigeria
- 2022
-
Ingår i: Remote Sensing Applications: Society and Environment. - : Elsevier BV. - 2352-9385. ; 27
-
Tidskriftsartikel (refereegranskat)abstract
- The urbanization of landscapes and the increase in impervious land cover materials is known to cause significant changes in the landscape's thermal properties, typically leading to urban heat island (UHI). Although previous studies have investigated the impacts of land cover land use (LULC) and other factors on the urban land surface temperature (LST), the results of such studies are mixed. For instance, it is not yet clear what factors affect the spatial and temporal variation of the relationship between LULC and the LST, as well as the exact trajectory through which identified factors affect the thermal character of the urban landscape. In the current study, we examined the relationship between LULC, elevation and LST in Ilorin from the period of 2002–2020. The overriding aim was to understand the degree of association between LULC, elevation and LST, and the drivers of the spatial and temporal variation in the observed relationship. LST and NDVI were derived from Landsat data products. LST was derived using a mono-window algorithm and NDVI was used as proxy for LULC. The spatial pattern of LULC was analyzed using Moran's I spatial autocorrelation statistics. To investigate the relationship between LULC, elevation and LST, we adopted both ordinary least square (OLS) regression models and the geographically weighted regression (GWR) method to reveal both the linear and the geographically varying relationship between the LULC, elevation and LST. The results of the study show that the LULC pattern of Ilorin has been significantly altered during the 2000 to 2020 period. The urban proportion of the landscape has shown a significant increase, rising by more than 11% relative to 2002 figures, and the vegetation proportion, especially the forest component, has diminished within same temporal extent. LST values varied in both space and time, with high temperature clusters noticeable in the built-up areas and decreasing towards the urban periphery. The result of the autocorrelation analysis using Moran's I index reveals a significant clustering of LST in all the epochs investigated. Across the study area, minimum and maximum LST values of 0 °C and 41 °C were recorded in 2002 and 2020 respectively. Statistically significant relationships were observed between LULC, elevation and LST. However, the relationship between elevation and LST was very weak. Temporally, the strength of the relationship between the variables (as indicated in the variables' coefficient) as well as the overall model predictive performance (indicated by in the R2) fluctuated over the years. Spatially, the strength of relationship between LST and LULC and elevation varied significantly. LULC explained approximately between 26% and 64% of total LST variation in the city between 2002 and 2020. The study findings are relevant for efforts geared towards alleviating the degree of UHI or its impacts, generally, and in the city of Ilorin, in particular. An understanding of the spatial distribution of LULC and their impacts on the LST can be helpful in identifying areas needing attention. The observed relationship between relevant LULC classes can be incorporated into urban planning strategies to ensure a sustainable city development.
|
|
| 8. |
- Rudke, A. P., et al.
(författare)
-
Mapping past landscapes using landsat data : Upper Paraná River Basin in 1985
- 2021
-
Ingår i: Remote Sensing Applications: Society and Environment. - : Elsevier BV. - 2352-9385. ; 21
-
Tidskriftsartikel (refereegranskat)abstract
- During the last decades, the science of remote sensing of the Earth's surface has produced an enormous amount of data. In parallel, with the increase in computational capacity, several classification methods have been applied to the satellite retrievals. This timely combination allows recovering more accurate knowledge about the land cover maps of past times. Therefore, the main goal of this work was to develop a land cover product for the year 1985 in the Upper Paraná River Basin (UPRB-1985), one of the largest and most economically important river basins in the world. The land cover map was developed using a supervised classifier - SVM (Support Vector Machine) applied to data from Landsat TM (Thematic Mapper) sensor. The classification process was carried out based on 52 scenes collected during 1985 and a total of 17,040 training samples across the basin. Pixel and Object-based methods were used to classify Landsat scenes. The generated mapping accuracy was assessed using statistical criteria adopted in the literature - Global Accuracy and Kappa Index. The McNemar's test result showed no significant differences (at the 5% level) between the Pixel-based and Object-based classifications, even with the Object-based classification accuracy was slightly higher (Global Accuracy of 79.8%). However, some relationship between the relief and the classification approach was observed. In sub-basins with high slopes, the mean overall accuracy values of the Pixel-based classification approach were 13.1% higher than the Object-based approach. By mapping past land cover, this work is strategic information to understand ongoing processes, as well as to assess changes in land cover that have occurred over time and evaluate to what extent they explain the variability in the hydrology of the region.
|
|
