ABSTRACT
Frequent floods are a severe threat to the well-being of people the world over. This is particularly severe in developing countries like India where tropical monsoon climate prevails. Recently, flood hazard susceptibility mapping has become a popular tool to mitigate the effects of this threat. Therefore, the present study utilized four distinctive Machine Learning algorithms i.e., K-Nearest Neighbor, Decision Tree, Naive Bayes, and Random Forest to estimate flood susceptibility zones in the Agartala Urban Watershed of Tripura, India. The latter experiences debilitating floods during the monsoon season. A multicollinearity test was conducted to examine the collinearity of the chosen flood conditioning factors, and it was seen that none of the factors were compromised by multicollinearity. Results showed that around three-fourths of the AUW area was classified as moderate to very high flood-prone zones, while over 20 percent was between low and very low flood-prone zones. The models applied performed well with ROC-AUC scores greater than 70 percent and MAE, MSE, and RMSE scores less than 30 percent. DT and RF algorithms were suggested for places with similar physical characteristics based on their outstanding performance and the training datasets. The study provides valuable insights to policymakers, administrative authorities, and local stakeholders to cope with floods and enhance flood prevention measures as a climate change adaptation strategy in the AUW.
Subject(s)
Environmental Monitoring , Floods , Humans , Bayes Theorem , Environmental Monitoring/methods , Algorithms , Machine Learning , IndiaABSTRACT
Railways are an indispensable component of sustainable transportation systems, but also exact a toll on wildlife. Wild Asian elephants are often killed by trains in Assam, India, where we assess temporal variations in the occurrences of elephant-train collisions (ETCs) and casualties during 1990-2018. This study also assesses spatially varying relationships between elephant-train collision (ETC) rates and elephant and train densities in the adjoining 10 km2 grid cells of 11 prioritized railroad segments using ordinary least squares (OLS) and geographically weighted regression (GWR) models. The temporal analysis indicated that ETCs spiked at certain hours and months. The adult and calf elephant casualties on the railroads were found to be two to fivefold high during the post monsoon season compared to other seasons. During the operation period of meter gauge railroads (1990-1997), the proportions of ETCs and casualties were only 15.6% and 8.7% respectively. However, these increased substantially to 84.4% and 91.3% respectively during the operation of broad gauge railroads (1998-2018). The OLS model indicated that both elephant and train densities explained 37% of the variance of ETC rate, while GWR model showed 83% of the variance of ETC rate. The local coefficient values of GWR indicated that both the predictor variables interplayed significantly and positively to determine ETC rates in the Mariani-Nakachari and Khatkhati-Dimapur railroad segments. However, the relationship between ETC rate and elephant density is significantly negative in the Habaipur-Diphu railroad, implying that the elephant population along this railroad stretch is significantly affected by railways through large scale ETCs. Hence, there is an urgent need to address long-term mitigation strategies so that elephants can be conserved by providing safe passages and survival resources along railway lines.
Subject(s)
Elephants , Railroads , Animals , Animals, Wild , India , Seasons , Spatial RegressionABSTRACT
Spatially explicit information on forest management at a global scale is critical for understanding the status of forests, for planning sustainable forest management and restoration, and conservation activities. Here, we produce the first reference data set and a prototype of a globally consistent forest management map with high spatial detail on the most prevalent forest management classes such as intact forests, managed forests with natural regeneration, planted forests, plantation forest (rotation up to 15 years), oil palm plantations, and agroforestry. We developed the reference dataset of 226 K unique locations through a series of expert and crowdsourcing campaigns using Geo-Wiki ( https://www.geo-wiki.org/ ). We then combined the reference samples with time series from PROBA-V satellite imagery to create a global wall-to-wall map of forest management at a 100 m resolution for the year 2015, with forest management class accuracies ranging from 58% to 80%. The reference data set and the map present the status of forest ecosystems and can be used for investigating the value of forests for species, ecosystems and their services.
Subject(s)
Conservation of Natural Resources , Forests , EcosystemABSTRACT
In recent decades, South Asia has experienced declining air quality, with much of the attention being focused on extremely high levels of particulate matter. Here, we analyze tropospheric ozone (O3), formaldehyde (HCHO), and nitrogen dioxide (NO2) to assess other measures of air quality across South Asia from 2008 to 2018. The IASI-Forli retrieved tropospheric ozone data was validated with ozonesonde, reanalysis (ERA5), satellite (TES), and model simulation products (GEOS-Chem and TOMCAT/SLIMCAT). Space-based observations of these three trace gases were used to conduct a spatio temporal analysis over South Asia using trend analysis (Theil-Sen and linear regression), change-point detection (Pettitt's test), and hotspot identification (Getis-Ord Gi*). We used the formaldehyde-nitrogen dioxide ratio (FNR) to identify NOx limited, VOC limited, and transitional regimes in South Asia. Counter to previous studies, a statistically significant decrease of HCHO (-0.0041 DU yr-1) and O3 (-0.064 DU yr-1) was detected for South Asia; however, NO2 is increasing the 0.001 DU yr-1 over South Asia during 2008-18. The Indo-Gangetic Plains emerged as being critically affected by the three trace gases. Certain parts of southern and south-eastern India are gradually emerging as NO2 and HCHO hotpots. No significant O3 hotspots were discernible, though coldspots existed along the Himalaya belt of India, Nepal, and Bhutan and mountainous tracts of Pakistan. FNR indicates the reduction of NOx in NOx-limited regime of the Indo-Gangetic Plains reduced the formation of tropospheric O3 over South Asia.
Subject(s)
Air Pollutants , Environmental Pollutants , Ozone , Air Pollutants/analysis , Environmental Monitoring , India , Nitrogen Dioxide/analysis , Ozone/analysisABSTRACT
There is an increasing evidence that smallholder farms contribute substantially to food production globally, yet spatially explicit data on agricultural field sizes are currently lacking. Automated field size delineation using remote sensing or the estimation of average farm size at subnational level using census data are two approaches that have been used. However, both have limitations, for example, automatic field size delineation using remote sensing has not yet been implemented at a global scale while the spatial resolution is very coarse when using census data. This paper demonstrates a unique approach to quantifying and mapping agricultural field size globally using crowdsourcing. A campaign was run in June 2017, where participants were asked to visually interpret very high resolution satellite imagery from Google Maps and Bing using the Geo-Wiki application. During the campaign, participants collected field size data for 130 K unique locations around the globe. Using this sample, we have produced the most accurate global field size map to date and estimated the percentage of different field sizes, ranging from very small to very large, in agricultural areas at global, continental, and national levels. The results show that smallholder farms occupy up to 40% of agricultural areas globally, which means that, potentially, there are many more smallholder farms in comparison with the two different current global estimates of 12% and 24%. The global field size map and the crowdsourced data set are openly available and can be used for integrated assessment modeling, comparative studies of agricultural dynamics across different contexts, for training and validation of remote sensing field size delineation, and potential contributions to the Sustainable Development Goal of Ending hunger, achieve food security and improved nutrition and promote sustainable agriculture.
Subject(s)
Crowdsourcing/statistics & numerical data , Farms , Satellite Imagery , AgricultureABSTRACT
A global reference data set on cropland was collected through a crowdsourcing campaign using the Geo-Wiki crowdsourcing tool. The campaign lasted three weeks, with over 80 participants from around the world reviewing almost 36,000 sample units, focussing on cropland identification. For quality assessment purposes, two additional data sets are provided. The first is a control set of 1,793 sample locations validated by students trained in satellite image interpretation. This data set was used to assess the quality of the crowd as the campaign progressed. The second data set contains 60 expert validations for additional evaluation of the quality of the contributions. All data sets are split into two parts: the first part shows all areas classified as cropland and the second part shows cropland average per location and user. After further processing, the data presented here might be suitable to validate and compare medium and high resolution cropland maps generated using remote sensing. These could also be used to train classification algorithms for developing new maps of land cover and cropland extent.