scholarly journals Wildfire Probability Mapping: Bivariate vs. Multivariate Statistics

2019 ◽  
Vol 11 (6) ◽  
pp. 618 ◽  
Author(s):  
Abolfazl Jaafari ◽  
Davood Mafi-Gholami ◽  
Binh Thai Pham ◽  
Dieu Tien Bui
Keyword(s):  
Multivariate Statistics ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Predictive Accuracy ◽  
Rank Test ◽  
Wind Effect ◽  
Ensemble Modeling ◽  
Residential Areas ◽  
Topographic Wetness Index ◽  
Distribution Maps

Wildfires are one of the most common natural hazards worldwide. Here, we compared the capability of bivariate and multivariate models for the prediction of spatially explicit wildfire probability across a fire-prone landscape in the Zagros ecoregion, Iran. Dempster–Shafer-based evidential belief function (EBF) and the multivariate logistic regression (LR) were applied to a spatial dataset that represents 132 fire events from the period of 2007–2014 and twelve explanatory variables (altitude, aspect, slope degree, topographic wetness index (TWI), annual temperature, and rainfall, wind effect, land use, normalized difference vegetation index (NDVI), and distance to roads, rivers, and residential areas). While the EBF model successfully characterized each variable class by four probability mass functions in terms of wildfire probabilities, the LR model identified the variables that have a major impact on the probability of fire occurrence. Two distribution maps of wildfire probability were developed based upon the results of each model. In an ensemble modeling perspective, we combined the two probability maps. The results were verified and compared by the receiver operating characteristic (ROC) and the Wilcoxon Signed-Rank Test. The results showed that although an improved predictive accuracy (AUC = 0.864) can be achieved via an ensemble modeling of bivariate and multivariate statistics, the models fail to individually provide a satisfactory prediction of wildfire probability (EBFAUC = 0.701; LRAUC = 0.728). From these results, we recommend the employment of ensemble modeling approaches for different wildfire-prone landscapes.

scholarly journals Identification of Surface Water Storing Sites Using Topographic Wetness Index (TWI) and Normalized Difference Vegetation Index (NDVI)

2018 ◽  
Vol 8 ◽  
pp. 91-100
Author(s):  
Belete Berhanu ◽  
Ethiopia Bisrat
Keyword(s):  
Surface Water ◽  
Water Resource ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Cost Effective ◽  
Water Shortage ◽  
Sample Volume ◽  
Runoff Generation ◽  
Topographic Wetness Index ◽  
Wetness Index

Ethiopia is endowed with water and has a high runoff generation area compared to many countries, but the total stored water only goes up to approximately 36BCM. The problem of water shortage in Ethiopia emanates from the seasonality of rainfall and the lack of infrastructure for storage to capture excess runoff during flood seasons. Based on this premise, a method for a syndicate use of topography, land use and vegetation was applied to locate potential surface water storing sites. The steady-state Topographic Wetness Index (TWI) was used to represent the spatial distribution of water flow and water stagnating across the study area and the Normalized Difference Vegetation Index (NDVI) was used to detect surface water through multispectral analysis. With this approach, a number of water storing sites were identified in three categories: primary sources (water bodies based), secondary sources (Swampy/wetland based) and tertiary sources (the land based). A sample volume analysis for the 120354 water storing sites in category two, gives a 44.92BCM potential storing capacity with average depth of 4 m that improves the annual storage capacity of the country to 81BCM (8.6 % of annual renewable water sources). Finally, the research confirmed the TWI and NDVI based approach for water storing sites works without huge and complicated earth work; it is cost effective and has the potential of solving complex water resource challenges through spatial representation of water resource systems. Furthermore, the application of remote sensing captures temporal diversity and includes repetitive archives of data, enabling the monitoring of areas, even those that are inaccessible, at regular intervals.

scholarly journals Estimation of different data compositions for early-season crop type classification

PeerJ ◽  
2018 ◽  
Vol 6 ◽  
pp. e4834 ◽  
Author(s):  
Pengyu Hao ◽  
Mingquan Wu ◽  
Zheng Niu ◽  
Li Wang ◽  
Yulin Zhan
Keyword(s):  
Time Series ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Remote Sensing Data ◽  
Classification Performance ◽  
Distribution Maps ◽  
Production Forecasting ◽  
Crop Type ◽  
Ndvi Time Series ◽  
Multi Temporal

Timely and accurate crop type distribution maps are an important inputs for crop yield estimation and production forecasting as multi-temporal images can observe phenological differences among crops. Therefore, time series remote sensing data are essential for crop type mapping, and image composition has commonly been used to improve the quality of the image time series. However, the optimal composition period is unclear as long composition periods (such as compositions lasting half a year) are less informative and short composition periods lead to information redundancy and missing pixels. In this study, we initially acquired daily 30 m Normalized Difference Vegetation Index (NDVI) time series by fusing MODIS, Landsat, Gaofen and Huanjing (HJ) NDVI, and then composited the NDVI time series using four strategies (daily, 8-day, 16-day, and 32-day). We used Random Forest to identify crop types and evaluated the classification performances of the NDVI time series generated from four composition strategies in two studies regions from Xinjiang, China. Results indicated that crop classification performance improved as crop separabilities and classification accuracies increased, and classification uncertainties dropped in the green-up stage of the crops. When using daily NDVI time series, overall accuracies saturated at 113-day and 116-day in Bole and Luntai, and the saturated overall accuracies (OAs) were 86.13% and 91.89%, respectively. Cotton could be identified 40∼60 days and 35∼45 days earlier than the harvest in Bole and Luntai when using daily, 8-day and 16-day composition NDVI time series since both producer’s accuracies (PAs) and user’s accuracies (UAs) were higher than 85%. Among the four compositions, the daily NDVI time series generated the highest classification accuracies. Although the 8-day, 16-day and 32-day compositions had similar saturated overall accuracies (around 85% in Bole and 83% in Luntai), the 8-day and 16-day compositions achieved these accuracies around 155-day in Bole and 133-day in Luntai, which were earlier than the 32-day composition (170-day in both Bole and Luntai). Therefore, when the daily NDVI time series cannot be acquired, the 16-day composition is recommended in this study.

scholarly journals Assessing Correlation of High-Resolution NDVI with Fertilizer Application Level and Yield of Rice and Wheat Crops using Small UAVs

2019 ◽  
Vol 11 (2) ◽  
pp. 112 ◽  
Author(s):  
Senlin Guan ◽  
Koichiro Fukami ◽  
Hitoshi Matsunaka ◽  
Midori Okami ◽  
Ryo Tanaka ◽  
...  
Keyword(s):  
High Resolution ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Ground Level ◽  
Fertilizer Application ◽  
Alignment Algorithm ◽  
Distribution Maps ◽  
Ripening Stages ◽  
Highly Correlated ◽  
Multispectral Sensing

The aim of this study was to use small unmanned aerial vehicles (UAVs) for determining high-resolution normalized difference vegetation index (NDVI) values. Subsequently, these results were used to assess their correlations with fertilizer application levels and the yields of rice and wheat crops. For multispectral sensing, we flew two types of small UAVs (DJI Phantom 4 and DJI Phantom 4 Pro)—each equipped with a compact multispectral sensor (Parrot Sequoia). The information collected was composed of numerous RGB orthomosaic images as well as reflectance maps with spatial resolution greater than a ground sampling distance of 10.5 cm. From 223 UAV flight campaigns over 120 fields with a total area coverage of 77.48 ha, we determined that the highest efficiency for the UAV-based remote sensing measurement was approximately 19.8 ha per 10 min while flying 100 m above ground level. During image processing, we developed and used a batch image alignment algorithm—a program written in Python language–to calculate the NDVI values in experimental plots or fields in a batch of NDVI index maps. The color NDVI distribution maps of wide rice fields identified differences in stages of ripening and lodging-injury areas, which accorded with practical crop growth status from aboveground observation. For direct-seeded rice, variation in the grain yield was most closely related to that in the NDVI at the early reproductive and late ripening stages. For wheat, the NDVI values were highly correlated with the yield ( R 2 = 0.601–0.809) from the middle reproductive to the early ripening stages. Furthermore, using the NDVI values, it was possible to differentiate the levels of fertilizer application for both rice and wheat. These results indicate that the small UAV-derived NDVI values are effective for predicting yield and detecting fertilizer application levels during rice and wheat production.

A data-driven approach to quantifying urban evapotranspiration using remote sensing, footprint modeling, and deep learning

2021 ◽  
Author(s):  
Stenka Vulova ◽  
Fred Meier ◽  
Alby Duarte Rocha ◽  
Justus Quanz ◽  
Hamideh Nouri ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Land Surface ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Predictive Accuracy ◽  
Meteorological Data ◽  
Model Performance ◽  
Urban Structure ◽  
Flux Footprint ◽  
Gis Data

<p>An increasing number of urban residents are affected by the urban heat island effect and water scarcity as urbanization and climate change progress. Evapotranspiration (ET) is a key component of urban greening measures aimed at addressing these issues, yet methods to estimate urban ET have thus far been limited. In this study, we present a novel approach to model urban ET at a half-hourly scale by fusing flux footprint modeling, remote sensing (RS) and geographic information system (GIS) data, and artificial intelligence (AI). We investigated this approach with a two-year dataset (2018-2020) from two eddy flux towers in Berlin, Germany. Two AI algorithms (1D convolutional neural networks and random forest) were compared. The land surface characteristics contributing to ET measurements were estimated by combining footprint modeling with RS and GIS data, which included Normalized Difference Vegetation Index (NDVI) derived from the Harmonized Landsat and Sentinel-2 (HLS) NASA product and indicators of 3D urban structure (e.g. building height). The contribution of remote sensing and meteorological data to model performance was examined by testing four predictor scenarios: (1) only reference evapotranspiration (ETo), (2) ETo and RS/ GIS data, (3) meteorological data, and (4) meteorological and RS/ GIS data. The inclusion of GIS and RS data extracted using flux footprints improved the predictive accuracy of models. The best-performing models were then used to model ET values for the year 2019 and compute monthly and annual sums of ET. A variable importance analysis highlighted the importance of the NDVI and impervious surface fraction in modeling urban ET. The 2019 ET sum was considerably higher at the site surrounded by more urban vegetation (366 mm) than at the inner-city site (223 mm). The proposed method is highly promising for modeling ET in a heterogeneous urban environment and can bolster sustainable urban planning efforts.</p>

scholarly journals Analysis of Development Patterns of Built Land and Spatial Structure in Bandung City Using Landsat 8 Image Data

2021 ◽  
Vol 19 (1) ◽  
pp. 36-42
Author(s):  
Mukhoriyah Mukhoriyah ◽  
Samsul Arifin ◽  
Esthi Kurnia Dewi ◽  
Silvia Silvia
Keyword(s):  
Spatial Structure ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Image Data ◽  
Development Pattern ◽  
Landsat 8 ◽  
Residential Areas ◽  
City Center ◽  
Catchment Areas ◽  
The City

The development of an urban area and the increasing totally of population growth greatly affect the need for land. To satisfy these needs, the land changes into built land which causes the density of an area. This study aims to analyze the development pattern of built land and the spatial structure of Bandung City. The data used are the 2015-2020 Landsat 8 time series imagery, the 2019 SPOT-6 imagery, and the administrative boundary map. The analytical methods used to identify and differentiate between built and non-built land classes are NDVI (Normalized Difference Vegetation Index) and the OTSU method with a threshold of 0.1. Based on the analysis, the results obtained are that the changes in the area of built and non-built land in 2015 amounted to 7,115.9 Ha and in 2017 it was 5,977.3 Ha and for 2 years the area decreased by 4%. Meanwhile, in 2017-2019 there was an increase of 2%, and in 2020 it decreased by 2% again. Based on the results of the analysis, the development pattern of land developed in the city of Bandung generally spreads from the city center to the suburbs, which are used as service / government centers, trade and service areas, and infrastructure. With this spreading pattern, the spatial structure is in the form of multiple nuclei or evenly distributed throughout the city of Bandung, where the City Center or CBD is used as a landmark for the surrounding areas. The high development pattern of built land has an impact on the surrounding environment, especially residential areas that have high building density causing the settlement area to become slum and reduce water catchment areas. The conclusion of this study is that the changes in the built-in land from 2015-2020 decreased by 3%, with the development pattern of the constructed land spreading out following the form of the road network, both arterial, collector and local roads.

scholarly journals Association between the First Occurrence of Asthma and Residential Greenness in Children and Teenagers in Taiwan

2019 ◽  
Vol 16 (12) ◽  
pp. 2076 ◽  
Author(s):  
Chia-Jung Hsieh ◽  
Pei-Ying Yu ◽  
Chun-Ju Tai ◽  
Rong-Hwa Jan ◽  
Tzai-Hung Wen ◽  
...  
Keyword(s):  
Vegetation Index ◽  
Green Space ◽  
Normalized Difference Vegetation Index ◽  
Family Income ◽  
Conditional Logistic Regression ◽  
Systematic Sampling ◽  
Residential Areas ◽  
Space Design ◽  
Increased Risk ◽  
First Occurrence

Green spaces have benefits but may also increase the risk of allergic disease. This study examined the association between the first occurrence of asthma and greenness exposure in children and teenagers. We conducted a 1:1 matched case-control study matched by sex, age, and the first diagnosis year with 7040 eligible subjects from a systematic sampling cohort database in Taiwan from 2001 to 2013. A normalized difference vegetation index (NDVI) value ≥0.4 was used as the criterion to determine the green space. The green cover images were then transformed to the green coverage rate in the township surrounding the residential areas of the asthma and control subjects. Conditional logistic regression analyses demonstrated that a significantly increased risk of asthma in preschool children was associated with the surrounding greenness after adjusting for urbanization level, frequency of healthcare provider visits, mean township family income, CO, NOx, and PM2.5. The risk of asthma occurrence increased significantly with increasing greenness exposure (p-trend < 0.05). Nevertheless, exposure to the highest greenness levels (81–100%) was not associated with a significantly higher risk of asthma occurrence than was exposure to the lowest values (0–20%) of greenness. This study suggests that green space design should consider more effective methods of reducing the allergy impact.

scholarly journals Determining the terrain characteristics related to the surface expression of subsurface water pressurization in permafrost landscapes using susceptibility modelling

2017 ◽  
Vol 11 (3) ◽  
pp. 1403-1415 ◽  
Author(s):  
Jean E. Holloway ◽  
Ashley C. A. Rudy ◽  
Scott F. Lamoureux ◽  
Paul M. Treitz
Keyword(s):  
Active Layer ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Additive Model ◽  
The Arctic ◽  
Subsurface Water ◽  
Permafrost Degradation ◽  
Topographic Wetness Index ◽  
Landscape Degradation ◽  
Terrain Characteristics

Abstract. Warming of the Arctic in recent years has led to changes in the active layer and uppermost permafrost. In particular, thick active layer formation results in more frequent thaw of the ice-rich transient layer. This addition of moisture, as well as infiltration from late season precipitation, results in high pore-water pressures (PWPs) at the base of the active layer and can potentially result in landscape degradation. To predict areas that have the potential for subsurface pressurization, we use susceptibility maps generated using a generalized additive model (GAM). As model response variables, we used active layer detachments (ALDs) and mud ejections (MEs), both formed by high PWP conditions at the Cape Bounty Arctic Watershed Observatory, Melville Island, Canada. As explanatory variables, we used the terrain characteristics elevation, slope, distance to water, topographic position index (TPI), potential incoming solar radiation (PISR), distance to water, normalized difference vegetation index (NDVI; ME model only), geology, and topographic wetness index (TWI). ALDs and MEs were accurately modelled in terms of susceptibility to disturbance across the study area. The susceptibility models demonstrate that ALDs are most probable on hill slopes with gradual to steep slopes and relatively low PISR, whereas MEs are associated with higher elevation areas, lower slope angles, and areas relatively far from water. Based on these results, this method identifies areas that may be sensitive to high PWPs and helps improve our understanding of geomorphic sensitivity to permafrost degradation.

scholarly journals A Deterministic Topographic Wetland Index Based on LiDAR-Derived DEM for Delineating Open-Water Wetlands

Water ◽  
2021 ◽  
Vol 13 (18) ◽  
pp. 2487
Author(s):  
Linlong Bian ◽  
Assefa M. Melesse ◽  
Arturo S. Leon ◽  
Vivek Verma ◽  
Zeda Yin
Keyword(s):  
Remote Sensing ◽  
Supervised Classification ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Ground Truth ◽  
Open Water ◽  
Training Data ◽  
Wetland Delineation ◽  
Topographic Wetness Index ◽  
Water Index

Wetlands play a significant role in flood mitigation. Remote sensing technologies as an efficient and accurate approach have been widely applied to delineate wetlands. Supervised classification is conventionally applied for remote sensing technologies to improve the wetland delineation accuracy. However, performing supervised classification requires preparing the training data, which is also considered time-consuming and prone to human mistakes. This paper presents a deterministic topographic wetland index to delineate wetland inundation areas without performing supervised classification. The classic methods such as Normalized Difference Vegetation Index, Normalized Difference Water Index, and Topographic Wetness Index were chosen to compare with the proposed deterministic topographic method on wetland delineation accuracy. The ground truth sample points validated by Google satellite imageries from four different years were used for the assessment of the delineation overall accuracy. The results show that the proposed deterministic topographic wetland index has the highest overall accuracy (98.90%) and Kappa coefficient (0.641) among the selected approaches in this study. The findings of this paper will provide an alternative approach for delineating wetlands rapidly by using solely the LiDAR-derived Digital Elevation Model.

scholarly journals Satellite image processing of the Buxus hyrcana Pojark dieback in the Northern Forests of Iran

2021 ◽  
Vol 67 (No. 2) ◽  
pp. 71-79
Author(s):  
Marzieh Ghavidel ◽  
Peyman Bayat ◽  
Mohammad Ebrahim Farashiani
Keyword(s):  
Image Processing ◽  
Disease Progression ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Satellite Image ◽  
Leaf Size ◽  
Disease Spread ◽  
Landsat 8 ◽  
Distribution Maps ◽  
Satellite Image Processing

Pests and diseases can cause a variety of reactions in plants. In recent years, the boxwood dieback has become one of the essential concerns of practitioners and natural resources managers in Iran. To control the boxwood dieback spread, the early detection and disease distribution maps are required. The boxwood dieback causes a range of changes in colour, shape and leaf size with respect to photosynthesis and transpiration. Through remote sensing techniques, e.g. satellite image processing data, the variation of thermal and visual characteristics of the plant could be used to measure and illustrate the symptoms of the disease. In this study, five common vegetation indices like difference vegetation index (DVI), normalized difference vegetation index (NDVI), soil adjusted vegetation index (SAVI), simple ratio (SR), and plant health index (PHI) were extracted and calculated from Landsat 8 satellite image data from six regions in the Gilan province, located in the northern part of Iran out of 150 maps over the time period 2014‒2018. It turned out that among the aforementioned indices, based upon the results of the models, SR and NDVI indices were more useful for the disease spread, respectively. Our disease progression model fitting criteria showed that this technique could probably be used to assess the extent of the affected areas and also the disease progression in the investigated regions in future.

scholarly journals Groundwater Site Prediction Using Remote Sensing, GIS and Statistical Approaches: A Case Study in the Western Desert, Iraq

2018 ◽  
Vol 7 (4.20) ◽  
pp. 166 ◽  
Author(s):  
Fadhil M. Shnewer ◽  
Alauldeen A. Hasan ◽  
Mudhaffar S. AL-Zuhairy
Keyword(s):  
Remote Sensing ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Spatial Relationship ◽  
Groundwater Potential ◽  
Western Desert ◽  
Geographical Information ◽  
Success Rates ◽  
Topographic Wetness Index ◽  
Conditioning Factors

Combination of remote sensing data and geographical information system (GIS) for the investigation of groundwater has become an advance approach in the researches of groundwater. The purpose of this research is to apply statistical models such as Evidential Belief Function (EBF) and Logistic Regression (LR) for mapping groundwater potential sites at Iraqi western desert (located at Al-Ramadi and Shithatha). The potential of the groundwater areas were determined depending on the spatial relationship between groundwater wells and different conditioning factors. These factors include altitude, curvature, aspect, slope, soil, normalized difference vegetation index (NDVI), topographic wetness index, fault, rainfall, stream density, stream power index, and lithology. The algorithms were used to model all layers of groundwater conditioning factors to generate groundwater probability areas. Then, the final maps included five potential classes i.e., very high, high, moderate, low and very low susceptible zones were generated. The final outcomes were validated using Area Under the Curve (AUC) algorithm. The values of success rates were 76.5% and 71.5% for EBF an LR respectively. The prediction rates for the same methods were 73.7% and 70%, respectively.  The thematic maps attained from the present study indicated the capability of EBF and LR methods in groundwater potential mapping.  

Sign in / Sign up

Export Citation Format

Share Document