Statistical analysis of active fire remote sensing data: examples from South Asia

2021 ◽  
Vol 193 (9) ◽  
Author(s):  
Jyoti U. Devkota
Keyword(s):  
Remote Sensing ◽  
Statistical Analysis ◽  
South Asia ◽  
Remote Sensing Data ◽  
Sensing Data ◽  
Active Fire

scholarly journals Deep Learning for Monitoring Agricultural Drought in South Asia Using Remote Sensing Data

2021 ◽  
Vol 13 (9) ◽  
pp. 1715
Author(s):  
Foyez Ahmed Prodhan ◽  
Jiahua Zhang ◽  
Fengmei Yao ◽  
Lamei Shi ◽  
Til Prasad Pangali Sharma ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
South Asia ◽  
Model Performance ◽  
Remote Sensing Data ◽  
Agricultural Drought ◽  
Gradient Boosting ◽  
Complex Nature ◽  
Sensing Data

Drought, a climate-related disaster impacting a variety of sectors, poses challenges for millions of people in South Asia. Accurate and complete drought information with a proper monitoring system is very important in revealing the complex nature of drought and its associated factors. In this regard, deep learning is a very promising approach for delineating the non-linear characteristics of drought factors. Therefore, this study aims to monitor drought by employing a deep learning approach with remote sensing data over South Asia from 2001–2016. We considered the precipitation, vegetation, and soil factors for the deep forwarded neural network (DFNN) as model input parameters. The study evaluated agricultural drought using the soil moisture deficit index (SMDI) as a response variable during three crop phenology stages. For a better comparison of deep learning model performance, we adopted two machine learning models, distributed random forest (DRF) and gradient boosting machine (GBM). Results show that the DFNN model outperformed the other two models for SMDI prediction. Furthermore, the results indicated that DFNN captured the drought pattern with high spatial variability across three penology stages. Additionally, the DFNN model showed good stability with its cross-validated data in the training phase, and the estimated SMDI had high correlation coefficient R2 ranges from 0.57~0.90, 0.52~0.94, and 0.49~0.82 during the start of the season (SOS), length of the season (LOS), and end of the season (EOS) respectively. The comparison between inter-annual variability of estimated SMDI and in-situ SPEI (standardized precipitation evapotranspiration index) showed that the estimated SMDI was almost similar to in-situ SPEI. The DFNN model provides comprehensive drought information by producing a consistent spatial distribution of SMDI which establishes the applicability of the DFNN model for drought monitoring.

scholarly journals Geostatistics of Active Fire Remote Sensing Data - Examples from South Asia

2021 ◽  
Author(s):  
Jyoti U. Devkota
Keyword(s):  
Remote Sensing ◽  
South Asia ◽  
Spatial Statistics ◽  
Geographical Location ◽  
Remote Sensing Data ◽  
Spatial Behavior ◽  
Spatial Error ◽  
Spatial Lag Model ◽  
Active Fire ◽  
Lag Model

Abstract Active fires illuminated on the earth surface are caught by the satellite. These fires are created by various sources such as vegetation fires, gas flares, biomass burning, volcanoes, and industrial sites such as steel mills. Near real time active fire data is collected using remote sensing techniques of satellites. Amount of active fires in an area is a proxy indicator of aerosols, green houses gases and trace gases. Here the behavior of active fires over a period of one year in Nepal, Bhutan and Srilanka are studied using spatial statistics. This study is based on data acquired through remote sensing of data acquisition platform, NASA’s MODIS. Spatial statistics is used here to study the incidence of active fires with respect to geographical location. The behavior of parameters of various autoregressive models like Spatial Durban Model, Spatial Lag Model, Spatial Error Model, Manski Model and Kelegian Prucha Model are minutely analyzed. The best model with highest pseudo R2 is selected. The spatial behavior of the fire radiative power for three countries is also predicted using spatial interpolation and kriging. So the burning potential of vegetations in unsampled areas is envisaged by thus predicting FRP. Such studies give a country wise perspective to the behavior of fire; this is with reference to south Asia. They are of great importance for countries of developing world which lack a strong backbone of good quality official records. Through the statistical analyses of data collected by such platforms, important information can be indirectly assessed.

scholarly journals Spectroscopy and Remote Sensing Techniques to Assess Active- and Post-Fire Effects

Proceedings ◽  
2020 ◽  
Vol 30 (1) ◽  
pp. 78
Author(s):  
Anna Brook
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Fire Effects ◽  
Sensing Data ◽  
The Past ◽  
Active Fire ◽  
Spectral Models ◽  
Post Fire Effects ◽  
Remote Sensing Techniques ◽  
Normalized Burn Ratio

Fires were once a natural phenomenon that helped to shape species distribution, contributed to the persistence of fire-dependent species, and assisted the natural evolution of ecosystems. However, nowadays, most of the forest fires worldwide are not of natural causes. Therefore, wildfires have received significant attention over the past few decades. Major ecological and policy changes were stimulated by historical frequency, extent, and severity of fires in the dry forests. These fires are important at both local to regional scales, as it might change the maintenance of landscape structure, composition, and function. Moreover, it affects pollutants, impacts air quality and raises human health risks. Many studies suggested using remote sensing data and techniques to assess fire characteristics and post-fire effects. Due to its ability to quantify patterns of variation in space and time, the remote sensing data are especially important to detect active fire extents at local and regional scales, mapping fuel loading and identify areas with long or problematic natural recovery. In the past few decades, the advantages of multi-temporal remote sensing techniques to monitor landscape change in a rapid and cost-effective manner, are reported in the scientific literature. Many studies focused on the development of techniques to evaluate and quantify fire behavior and fuel combustion. Yet the main contribution is recorded for spectral indices, e.g. the Normalized Burn Ratio (NBR), the difference in the Normalized Burn Ratio between pre- and post-fire images (dNBR), and the Normalized Difference Vegetation Index (NDVI), which are calculated by a simple combinations of different sensor bands, rely on spectral changes of the burning or burned surfaces. Numerous papers are focused on more advanced and very detailed spectral models of fuel and post-fire ash residues, mainly using laboratory spectrometers, e.g., Fourier Transform Infrared (FTIR). However, many of the developed models are not applicable in the real world. In the current talk, we will present the most recent studies and scientific activities in the field of (1) active fire detection and characterization, using mainly hyperspectral ground and airborne technologies; (2) future space-borne applications on board of nano- and micro-satellites; (3) discuss the contribution of detailed and precise spectral models for post-fire ecological effects studies; (4) describe field assessment; (5) discuss management applications and future directions of fire-related remote sensing research.

Assessment of the national market demand for high-resolution remote sensing data

2002 ◽  
Vol 8 (1) ◽  
pp. 15-22
Author(s):  
V.N. Astapenko ◽  
◽  
Ye.I. Bushuev ◽  
V.P. Zubko ◽  
V.I. Ivanov ◽  
...  
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Remote Sensing Data ◽  
Market Demand ◽  
Sensing Data ◽  
National Market

Processing of remote sensing data for detection and recognition of object classes

2004 ◽  
Vol 10 (5-6) ◽  
pp. 175-177
Author(s):  
S.L. Kravtsov ◽  
◽  
L.V. Oreshkina ◽  
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Sensing Data ◽  
Object Classes ◽  
Detection And Recognition
Sign in / Sign up

Export Citation Format

Share Document