Semi-automated land cover mapping using an ensemble of support vector machines with moderate resolution imagery integrated into a custom decision support tool

Land cover type is a fundamental remote sensing-derived variable for terrain analysis and environmental mapping applications. The currently available products are produced only for a single season or a specific year. Some of these products have a coarse resolution and quickly become outdated, as land cover type can undergo significant change over a short time period. In order to enable on-demand generation of timely and accurate land cover type products, we developed a sensor-agnostic framework leveraging pre-trained machine learning models. We also generated land cover models for Sentinel-2 (20m) and Landsat 8 imagery (30m) using either a single date of imagery or two dates of imagery for mapping land cover type. The two-date model includes 11 land cover type classes, whereas the single-date model contains 6 classes. The models’ overall accuracies were 84% (Sentinel-2 single date), 82% (Sentinel-2 two date), and 86% (Landsat 8 two date) across the continental United States. The three different models were built into an ArcGIS Pro Python toolbox to enable a semi-automated workflow for end users to generate their own land cover type maps on demand. The toolboxes were built using parallel processing and image-splitting techniques to enable faster computation and for use on less-powerful machines.

Urban Heat and Urban Cool Islands of Different Land Use Types in Cuiabá, Brazil

Urban heat islands (UHIs), urban cool islands (UCIs), and their varying effects due to land use/land cover types and the local climate were investigated from 2014 to 2015 in three urban zones located in Cuiabá city, Brazil, during hot-humid, and hot-dry periods. All the urban zones were analysed for land use/land cover type, local climate, and rate of warming and cooling based on the difference in air temperature (ΔT) between the urban zones and the rural zone located outside the urban perimeter. The annual UHI effect in all the urban zones exhibited varying intensities during the day, with the highest daytime intensity recorded after the sunrise. The duration of UHI effect varied with land use/land cover type; a consequence of high built-up density, verticalization, waterproof surface, and other peculiarities of urban areas. In the urban zones with high built-up density, the duration of UHI effect was observed for up to 24 h, while in the urban areas with low built-up density, the maximum duration of UHI effect was 8 h. On an average, during the daytime, the urban zone with approximately 70% of vegetation cover and water bodies recorded a UCI value of approximately –8 °C, whereas the urban zones with approximately 80% waterproof surface and bare land recorded a UCI value close to +2 °C during the hot-dry and hot-humid periods. The results indicate that land use and land cover types directly influence UHI intensity.

Spatio-Temporal Changes of Land Surface Temperature and the Influencing Factors in the Tarim Basin, Northwest China

Land surface temperature (LST) is an important parameter that affects the water cycle, environmental changes, and energy balance at global and regional scales. Herein, a time series analysis was conducted to estimate the monthly, seasonal, and interannual variations in LST during 2001–2019 in the Tarim Basin, China. Based on Moderate Resolution Imaging Spectroradiometer (MODIS) LST, air temperature, air pressure, relative humidity, wind speed, precipitation, elevation, and land-cover type data, we analyzed the spatio-temporal change characteristics of LST and the influencing factors. High LSTs occurred in the desert and plains and low LSTs occurred in surrounding mountain regions. The highest LST was recorded in July (25.1 °C) and the lowest was in January (−9.5 °C). On a seasonal scale, LST decreased in the order: summer > spring > autumn > winter. Annual LST showed an increasing trend of 0.2 °C/10 a in the desert and mountain areas, while the plains indicated a decreasing trend. In spring and autumn, western regions were dominated by a downward trend, whereas in winter a downward trend occurred in eastern regions. In summer, areas covered by vegetation were dominated by a downward trend, and desert and bare lands were dominated by an upward trend. Random forest (RF) model analysis showed that elevation was the most significant influencing factor (22.1%), followed by mean air temperature (20.1%). Correlation analysis showed that the main climatic factors air temperature, relative humidity, and elevation have a good correlation with the LST. Land-cover type also affected LST; during February–December the lowest LST was observed for permanent glacier snow and the highest was observed in the desert. El Nino and La Nina greatly influenced the LST variations. The North Atlantic Oscillation and Pacific Decadal Oscillation indices were consistent with the mean LST anomaly, indicating their considerable influence on LST variations.

Assessment of Dynamic Land System in Nilgiri Biosphere Reserve Using MODIS Derived Temporal Data Sets during 2001 to 2018

The Nilgiri Biosphere Reserve (NBR) is one of the largest protected ecologically sensitive areas in India. This study examined the land use/land cover (LULC) changes in NBR for past 18 years from 2001 to 2018 to figure out the LULC changed within a protected area using datasets in 2001, 2010, and 2018 with the help of pertinent geospatial techniques. MODIS Land Cover Type Product (MCD12Q1) accuracy was quantitatively analyzed based on ground truth data and Google Earth imagery. Validation of data were assessed using and overall 635 locations for its accuracy assessment. The obtained kappa coefficient of 0.75, denotes the classification has moderate accuracy. The results showed that in the past 18 years, woody savannas and grasslands were reduced by 299.47 sq.km and 155.32 sq.km respectively. The areas of croplands and cropland/natural vegetation mosaics were also increased by 34.84 sq.km and 54.41 sq.km, respectively. These results showed anthropogenic influences through agricultural practices within the NBR buffer zones. The mixed forests were increased by 266.01 sq.km. One of the significant changes was seen in closed shrublands, which were absent in 2018, that covered 1.50 sq.km in 2001. In addition, A gradual decrease in the area were noticed in woody savannas. From the outcomes, it is recommended that the LULC classes that cover minimal area may be unstable, so measures should be taken for their conservation. The study proved the usefulness of MODIS land cover type data in monitoring large areas periodically for quick decision-making.

Integrated Evaluation of Vegetation Drought Stress through Satellite Remote Sensing

In the coming decades, Bulgaria is expected to be affected by higher air temperatures and decreased precipitation, which will significantly increase the risk of droughts, forest ecosystem degradation and loss of ecosystem services (ES). Drought in terrestrial ecosystems is characterized by reduced water storage in soil and vegetation, affecting the function of landscapes and the ES they provide. An interdisciplinary assessment is required for an accurate evaluation of drought impact. In this study, we introduce an innovative, experimental methodology, incorporating remote sensing methods and a system approach to evaluate vegetation drought stress in complex systems (landscapes and ecosystems) which are influenced by various factors. The elevation and land cover type are key climate-forming factors which significantly impact the ecosystem’s and vegetation’s response to drought. Their influence cannot be sufficiently gauged by a traditional remote sensing-based drought index. Therefore, based on differences between the spectral reflectance of the individual natural land cover types, in a near-optimal vegetation state and divided by elevation, we assigned coefficients for normalization. The coefficients for normalization by elevation and land cover type were introduced in order to facilitate the comparison of the drought stress effect on the ecosystems throughout a heterogeneous territory. The obtained drought coefficient (DC) shows patterns of temporal, spatial, and interspecific differences on the response of vegetation to drought stress. The accuracy of the methodology is examined by field measurements of spectral reflectance, statistical analysis and validation methods using spectral reflectance profiles.

EVALUATION ON URBAN LAND EXPANSION QUALITY OF QINGDAO CITY FROM 2010 TO 2018

With the process of people moving from rural to urban area, the urban land boundary expanded significantly. In this paper, the urban land areas of Qingdao were extracted by using remote sensing images from 2010 to 2018. The spatiotemporal pattern of urban expansion in Qingdao city was revealed. Furthermore, the land cover type of the urban expansion area and urbanization rate were also analyzed to study the quality of urban expansion in different counties. It has shown that over 95% land cover types are impervious in the build-up areas of Qingdao, e.g. Shibei and Shinan district. However, there are more forest and water land exist in the suburban counties. The urban land expansion rate and people urbanization rate are highly related.

Potential Distribution of Colonizing Nine-Banded Armadillos at Their Northern Range Edge

The nine-banded armadillo (Dasypus novemcinctus) has become a recent addition to the local fauna of Illinois as a response to habitat alteration and climate change. This range expansion has resulted in the presence of armadillos in areas not predicted by earlier models. Although these models have been revised, armadillos continue to move north and have reached areas of heavy agricultural use. We identified conditions that favor the presence of armadillos and potential corridors for dispersal. Identifying the distribution of the armadillo in Illinois is a vital step in anticipating their arrival in areas containing potentially sensitive wildlife populations and habitats. Armadillo locations (n = 37) collected during 2016–2020 were used to develop a map of the potential distribution of armadillos in southern Illinois. Environmental data layers included in the model were land cover type, distance to water, distance to forest edge, human modification, and climactic variables. Land cover type was the most important contributing variable to the model. Our results are consistent with the tenet that armadillo activity and dispersal corridors are centered around riparian areas, and that forested cover may provide corridors an agricultural mosaic.

Comparison of Accuracy of Surface Temperature Images from Unmanned Aerial Vehicle and Satellite for Precise Thermal Environment Monitoring of Urban Parks Using In Situ Data

Rapid urbanization has led to several severe environmental problems, including so-called heat island effects, which can be mitigated by creating more urban green spaces. However, the temperature of various surfaces differs and precise measurement and analyses are required to determine the “coolest” of these. Therefore, we evaluated the accuracy of surface temperature data based on thermal infrared (TIR) cameras mounted on unmanned aerial vehicles (UAVs), which have recently been utilized for the spatial analysis of surface temperatures. Accordingly, we investigated land surface temperatures (LSTs) in green spaces, specifically those of different land cover types in an urban park in Korea. We compared and analyzed LST data generated by a thermal infrared (TIR) camera mounted on an unmanned aerial vehicle (UAV) and LST data from the Landsat 8 satellite for seven specific periods. For comparison and evaluation, we measured in situ LSTs using contact thermometers. The UAV TIR LST showed higher accuracy (R2 0.912, root mean square error (RMSE) 3.502 °C) than Landsat TIR LST accuracy (R2 value lower than 0.3 and RMSE of 7.246 °C) in all periods. The Landsat TIR LST did not show distinct LST characteristics by period and land cover type; however, grassland, the largest land cover type in the study area, showed the highest accuracy. With regard to the accuracy of the UAV TIR LST by season, the accuracy was higher in summer and spring (R2 0.868–0.915, RMSE 2.523–3.499 °C) than in autumn and winter (R2 0.766–0.79, RMSE 3.834–5.398 °C). Some land cover types (concrete bike path, wooden deck) were overestimated, showing relatively high total RMSEs of 4.439 °C and 3.897 °C, respectively, whereas grassland, which has lower LST, was underestimated—showing a total RMSE of 3.316 °C. Our results showed that the UAV TIR LST could be measured with sufficient reliability for each season and land cover type in an urban park with complex land cover types. Accordingly, our results could contribute to decision-making for urban spaces and environmental planning in consideration of the thermal environment.