Mapping global eco-environment vulnerability due to human and nature disturbances

Comprehensive drought risk assessment and mapping in Taiwan: An ANP-ANN ensemble approach

This study aims to comprehensively evaluate and map the risk of drought in Taiwan by employing a combination of two powerful models, the Analytic Network Process (ANP) and Artificial Neural Network (ANN). This innovative approach utilizes an ensemble learning method, where ANP constructs a logical network and assigns weights to various indicators. Subsequently, ANN leverages these weights to train the model effectively. A total of twenty indicators were incorporated into the analysis to create a holistic drought risk map for Taiwan. These indicators are thoughtfully categorized into three essential components: hazard, exposure, and vulnerability, providing a well-defined representation of drought risk. The trained ANN model showcases remarkable accuracy and performance, boasting values of 0.940 for accuracy, 0.946 for precision, 0.938 for recall, 0.942 for the F1 score, and 0.923 for the Kappa Index. These results unequivocally affirm the model's effectiveness in predicting drought risk. Furthermore, the final drought risk map underwent rigorous validation through fieldwork and statistical data. The validation process yielded high accuracies, ranging from 0.717 to 0.851, for assessing damage to crops, converted damaged areas, and estimated value product loss. This validation, conducted against multiple reference data sources, underscores the map's reliability and its alignment with various goodness-of-fit criteria. In summary, this study underscores the potency of the ANP-ANN ensemble approach, with the trained ANN model proving its robustness in swiftly predicting drought risk across diverse ecological and socioeconomic scenarios.

Demi-decadal land use land cover change analysis of Mizoram, India, with topographic correction using machine learning algorithm

Mizoram (India) is part of UNESCO's biodiversity hotspots in India that is primarily populated by tribes who engage in shifting agriculture. Hence, the land use land cover (LULC) pattern of the state is frequently changing. We have used Landsat 5 and 8 satellite images to prepare LULC maps from 2000 to 2020 in every 5 years. The atmospherically corrected images were pre-processed for removal of cloud cover and then classified into six classes: waterbodies, farmland, settlement, open forest, dense forest, and bare land. We applied four machine learning (ML) algorithms for classification, namely, random forest (RF), classification and regression tree (CART), minimum distance (MD), and support vector machine (SVM) for the images from 2000 to 2020. With 80% training and 20% testing data, we found that the RF classifier works best with the most accuracy than other classifiers. The average overall accuracy (OA) and Kappa coefficient (KC) from 2000 to 2020 were 84.00% and 0.79 when the RF classifier was used. When using SVM, CART, and MD, the average OA and KC were 78.06%, 0.73; 78.60%, 0.72; and 73.32%, 0.65, respectively. We utilised three methods of topographic correction, namely, C-correction, SCS (sun canopy sensor) correction, and SCS + C correction to reduce the misclassification due to shadow effects. SCS + C correction worked best for this region; hence, we prepared LULC maps on SCS + C corrected satellite image. Hence, we have used RF classifier for LULC preparation demi-decadal from 2000 to 2020. The OA for 2000, 2005, 2010, 2015, and 2020 was found to be 84%, 81%, 81%, 85%, and 89%, respectively, using RF. The dense forest decreased from 2000 to 2020 with an increase in open forest, settlement, and agriculture; nevertheless, when Farmland was low, there was an increase in the barren land. The results were significantly improved with the topographic correction, and misclassification was quite less.

Analysing food farming vulnerability in Kalimantan, Indonesia: Determinant factors and adaptation measures

As a result of plans to relocate the Indonesian capital city to East Kalimantan province, Kalimantan is expected to develop rapidly and the surrounding regencies and provinces will become food support areas for the new capital. However, the vulnerability of food farming in Kalimantan is a concern that must be addressed to ensure food security. This study aims to assess the vulnerability of food farming at the regency level of the island of Kalimantan, to assess the determinant factors of the food farming vulnerability and to compose adaptation measures that can reduce vulnerability. Socio economic, climate, water and land data are sorted and analyzed to represent the level of sensitivity and exposure index (SEI) and adaptive capacity index (ACI). Locations with 'High' and 'Very High' levels of farming vulnerability become interview sites with a total of 150 respondents. The results of the interviews strengthen the results of the vulnerability analysis which helps to determine the condition of farmers and food farming in vulnerable locations. The results indicated 'Very High' and 'High' level of vulnerability in 14 regencies/cities. Floods are climate-related disasters that most often affect farmers surveyed (46%), followed by droughts (30%) and pest attacks (24%) with significant impacts (49%). The identification of the determinant factors becomes the basis for adaptive measures to support decision-makers, local practitioners, and farmers by highlighting local challenges and proposing local-specific adaptation strategies.

A Land Use Classification Model Based on Conditional Random Fields and Attention Mechanism Convolutional Networks

Land use is used to reflect the expression of human activities in space, and land use classification is a way to obtain accurate land use information. Obtaining high-precision land use classification from remote sensing images remains a significant challenge. Traditional machine learning methods and image semantic segmentation models are unable to make full use of the spatial and contextual information of images. This results in land use classification that does not meet high-precision requirements. In order to improve the accuracy of land use classification, we propose a land use classification model, called DADNet-CRFs, that integrates an attention mechanism and conditional random fields (CRFs). The model is divided into two modules: the Dual Attention Dense Network (DADNet) and CRFs. First, the convolution method in the UNet network is modified to Dense Convolution, and the band-hole pyramid pooling module, spatial location attention mechanism module, and channel attention mechanism module are fused at appropriate locations in the network, which together form DADNet. Second, the DADNet segmentation results are used as a priori conditions to guide the training of CRFs. The model is tested with the GID dataset, and the results show that the overall accuracy of land use classification obtained with this model is 7.36% and 1.61% higher than FCN-8s and BiSeNet in classification accuracy, 11.95% and 1.81% higher in MIoU accuracy, and with a 9.35% and 2.07% higher kappa coefficient, respectively. The proposed DADNet-CRFs model can fully use the spatial and contextual semantic information of high-resolution remote sensing images, and it effectively improves the accuracy of land use classification. The model can serve as a highly accurate automatic classification tool for land use classification and mapping high-resolution images.

Spatially Balanced Sampling for Validation of GlobeLand30 Using Landscape Pattern-Based Inclusion Probability

Global and local land-cover mapping products provide important data on land surface. However, the accuracy of land-cover products is the key issue for their further scientific application. There has been neglect of the relationship between inclusion probability and spatial heterogeneity in traditional spatially balanced sampling. The aim of this paper was to propose an improved spatially balanced sampling method using landscape pattern-based inclusion probability. Compared with other global land-cover datasets, Globeland30 has the advantages of high resolution and high classification accuracy. A two-stage stratified spatially balanced sampling scheme was designed and applied to the regional validation of GlobeLand30 in China. In this paper, the whole area was divided into three parts: the Tibetan Plateau region, the Northwest China region, and the East China region. The results show that 7242 sample points were selected, and the overall accuracy of GlobeLand30-2010 in China was found to be 80.46%, which is close to the third-party assessment accuracy of GlobeLand30. This method improves the representativeness of samples, reduces the classification error of remote sensing, and provides better guidance for biodiversity and sustainable development of environment.

Spatial pattern of the ecological environment in Yunnan Province

Ecological science focuses on the structure and function of the natural environment. However, the study of ecological environments primarily focuses on single-element research and lacks a comprehensive perspective. To examine ecological environmental trends on different scales, the present paper selected Yunnan Province as the study area. Chemical oxygen demand, rocky desertification, forest coverage, natural disaster data and spatial analysis methods were used to obtain the ecological environmental characteristics of each county and construct a comprehensive evaluation method of the ecological environment. The present paper revealed that the environmental capacity in Yunnan Province was at a moderate level, the ecological environment fragility was remarkable, the significance of the ecological environment was very high, natural disasters occurred frequently, and spatial differentiation between ecological environments was obvious. The province may be divided into three functional areas: the comprehensive-balanced area, the efficiency-dominated area and the environment-dominated area. Central Yunnan was a key development zone and the main area for the manufacturing and service industries, which were built as a modern industrial system in Yunnan Province. The ecological environment in northwestern Yunnan and southern Yunnan is of high significance, and this region was an ecological environment protection area that was important area for the construction of the modern agricultural system in Yunnan Province. To achieve sustainable development of the ecological environment, the spatial characteristics of the ecological environment must be determined at the county scale.

Effects of lockdown due to COVID-19 outbreak on air quality and anthropogenic heat in an industrial belt of India

Highly urbanized and industrialized Asansol Durgapur industrial belt of Eastern India is characterized by severe heat island effect and high pollution level leading to human discomfort and even health problems. However, COVID-19 persuaded lockdown emergency in India led to shut-down of the industries, traffic system, and day-to-day normal work and expectedly caused changes in air quality and weather. The present work intended to examine the impact of lockdown on air quality, land surface temperature (LST), and anthropogenic heat flux (AHF) of Asansol Durgapur industrial belt. Satellite images and daily data of the Central Pollution Control Board (CPCB) were used for analyzing the spatial scale and numerical change of air quality from pre to amid lockdown conditions in the study region. Results exhibited that, in consequence of lockdown, LST reduced by 4.02 °C, PM10 level decreased from 102 to 18 μg/m3 and AHF declined from 116 to 40W/m2 during lockdown period. Qualitative upgradation of air quality index (AQI) from poor to very poor state to moderate to satisfactory state was observed during lockdown period. To regulate air quality and climate change, many steps were taken at global and regional scales, but no fruitful outcome was received yet. Such lockdown (temporarily) is against economic growth, but it showed some healing effect of air quality standard.

Classification and Observed Seasonal Phenology of Broadleaf Deciduous Forests in a Tropical Region by Using Multitemporal Sentinel-1A and Landsat 8 Data

Broadleaf deciduous forests (BDFs) or dry dipterocarp forests play an important role in biodiversity conservation in tropical regions. Observations and classification of forest phenology provide valuable inputs for ecosystem models regarding its responses to climate change to assist forest management. Remotely sensed observations are often used to derive the parameters corresponding to seasonal vegetation dynamics. Data acquired from the Sentinel-1A satellite holds a great potential to improve forest type classification at a medium-large scale. This article presents an integrated object-based classification method by using Sentinel-1A and Landsat 8 OLI data acquired during different phenological periods (rainy and dry seasons). The deciduous forest and nondeciduous forest areas are classified by using NDVI (normalized difference vegetation index) from Landsat 8 cloud-free composite images taken during dry (from February to April) and rainy (from June to October) seasons. Shorea siamensis Miq. (S. siamensis), Shorea obtusa Wall. ex Blume (S. obtusa), and Dipterocarpus tuberculatus Roxb. (D. tuberculatus) in the deciduous forest area are classified based on the correlation between phenology of BDFs in Yok Don National Park and backscatter values of time-series Sentinel-1A imagery in deciduous forest areas. One hundred and five plots were selected during the field survey in the study area, consisting of dominant deciduous species, tree height, and canopy diameter. Thirty-nine plots were used for training to decide the broadleaf deciduous forest areas of the classified BDFs by the proposed method, and the other sixty-six plots were used for validation. Our proposed approach used the changes of backscatter in multitemporal SAR images to implement BDF classification mapping with acceptable accuracy. The overall accuracy of classification is about 79%, with a kappa coefficient of 0.7. Accurate classification and mapping of the BDFs using the proposed method can help authorities implement forest management in the future.

Sentinel-2 Image Scene Classification: A Comparison between Sen2Cor and a Machine Learning Approach

Given the continuous increase in the global population, the food manufacturers are advocated to either intensify the use of cropland or expand the farmland, making land cover and land usage dynamics mapping vital in the area of remote sensing. In this regard, identifying and classifying a high-resolution satellite imagery scene is a prime challenge. Several approaches have been proposed either by using static rule-based thresholds (with limitation of diversity) or neural network (with data-dependent limitations). This paper adopts the inductive approach to learning from surface reflectances. A manually labeled Sentinel-2 dataset was used to build a Machine Learning (ML) model for scene classification, distinguishing six classes (Water, Shadow, Cirrus, Cloud, Snow, and Other). This models was accessed and further compared to the European Space Agency (ESA) Sen2Cor package. The proposed ML model presents a Micro-F1 value of 0.84, a considerable improvement when compared to the Sen2Cor corresponding performance of 0.59. Focusing on the problem of optical satellite image scene classification, the main research contributions of this paper are: (a) an extended manually labeled Sentinel-2 database adding surface reflectance values to an existing dataset; (b) an ensemble-based and a Neural-Network-based ML models; (c) an evaluation of model sensitivity, biasness, and diverse ability in classifying multiple classes over different geographic Sentinel-2 imagery, and finally, (d) the benchmarking of the ML approach against the Sen2Cor package.

Land-Use Land-Cover Classification by Machine Learning Classifiers for Satellite Observations—A Review

Rapid and uncontrolled population growth along with economic and industrial development, especially in developing countries during the late twentieth and early twenty-first centuries, have increased the rate of land-use/land-cover (LULC) change many times. Since quantitative assessment of changes in LULC is one of the most efficient means to understand and manage the land transformation, there is a need to examine the accuracy of different algorithms for LULC mapping in order to identify the best classifier for further applications of earth observations. In this article, six machine-learning algorithms, namely random forest (RF), support vector machine (SVM), artificial neural network (ANN), fuzzy adaptive resonance theory-supervised predictive mapping (Fuzzy ARTMAP), spectral angle mapper (SAM) and Mahalanobis distance (MD) were examined. Accuracy assessment was performed by using Kappa coefficient, receiver operational curve (RoC), index-based validation and root mean square error (RMSE). Results of Kappa coefficient show that all the classifiers have a similar accuracy level with minor variation, but the RF algorithm has the highest accuracy of 0.89 and the MD algorithm (parametric classifier) has the least accuracy of 0.82. In addition, the index-based LULC and visual cross-validation show that the RF algorithm (correlations between RF and normalised differentiation water index, normalised differentiation vegetation index and normalised differentiation built-up index are 0.96, 0.99 and 1, respectively, at 0.05 level of significance) has the highest accuracy level in comparison to the other classifiers adopted. Findings from the literature also proved that ANN and RF algorithms are the best LULC classifiers, although a non-parametric classifier like SAM (Kappa coefficient 0.84; area under curve (AUC) 0.85) has a better and consistent accuracy level than the other machine-learning algorithms. Finally, this review concludes that the RF algorithm is the best machine-learning LULC classifier, among the six examined algorithms although it is necessary to further test the RF algorithm in different morphoclimatic conditions in the future.

Consecutive Dual-Vortex Interactions between Quadruple Typhoons Noru, Kulap, Nesat and Haitang during the 2017 North Pacific Typhoon Season

This study utilizes remote sensing imagery, a differential averaging technique and empirical formulas (the ‘Liou–Liu formulas’) to investigate three consecutive sets of dual-vortex interactions between four cyclonic events and their neighboring environmental air flows in the Northwest Pacific Ocean during the 2017 typhoon season. The investigation thereby deepens the current understanding of interactions involving multiple simultaneous/sequential cyclone systems. Triple interactions between Noru–Kulap–Nesat and Noru–Nesat–Haitung were analyzed using geosynchronous satellite infrared (IR1) and IR3 water vapor (WV) images. The differential averaging technique based on the normalized difference convection index (NDCI) operator and filter depicted differences and generated a new set of clarified NDCI images. During the first set of dual-vortex interactions, Typhoon Noru experienced an increase in intensity and a U-turn in its direction after being influenced by adjacent cooler air masses and air flows. Noru’s track change led to Fujiwhara-type rotation with Tropical Storm Kulap approaching from the opposite direction. Kulap weakened and merged with Noru, which tracked in a counter-clockwise loop. Thereafter, in spite of a distance of 2000–2500 km separating Typhoon Noru and newly-formed Typhoon Nesat, the influence of middle air flows and jet flows caused an ‘indirect interaction’ between these typhoons. Evidence of this second interaction includes the intensification of both typhoons and changing track directions. The third interaction occurred subsequently between Tropical Storm Haitang and Typhoon Nesat. Due to their relatively close proximity, a typical Fujiwhara effect was observed when the two systems began orbiting cyclonically. The generalized Liou–Liu formulas for calculating threshold distances between typhoons successfully validated and quantified the trilogy of interaction events. Through the unusual and combined effects of the consecutive dual-vortex interactions, Typhoon Noru survived 22 days from 19 July to 9 August 2017 and migrated approximately 6900 km. Typhoon Noru consequently became the third longest-lasting typhoon on record for the Northwest Pacific Ocean. A comparison is made with long-lived Typhoon Rita in 1972, which also experienced similar multiple Fujiwhara interactions with three other concurrent typhoons.

Spatio–temporal Assessment of Drought in Ethiopia and the Impact of Recent Intense Droughts

The recent droughts that have occurred in different parts of Ethiopia are generally linked to fluctuations in atmospheric and ocean circulations. Understanding these large-scale phenomena that play a crucial role in vegetation productivity in Ethiopia is important. In view of this, several techniques and datasets were analyzed to study the spatio–temporal variability of vegetation in response to a changing climate. In this study, 18 years (2001–2018) of Moderate Resolution Imaging Spectroscopy (MODIS) Terra/Aqua, normalized difference vegetation index (NDVI), land surface temperature (LST), Climate Hazards Group Infrared Precipitation with Stations (CHIRPS) daily precipitation, and the Famine Early Warning Systems Network (FEWS NET) Land Data Assimilation System (FLDAS) soil moisture datasets were processed. Pixel-based Mann–Kendall trend analysis and the Vegetation Condition Index (VCI) were used to assess the drought patterns during the cropping season. Results indicate that the central highlands and northwestern part of Ethiopia, which have land cover dominated by cropland, had experienced decreasing precipitation and NDVI trends. About 52.8% of the pixels showed a decreasing precipitation trend, of which the significant decreasing trends focused on the central and low land areas. Also, 41.67% of the pixels showed a decreasing NDVI trend, especially in major parts of the northwestern region of Ethiopia. Based on the trend test and VCI analysis, significant countrywide droughts occurred during the El Niño 2009 and 2015 years. Furthermore, the Pearson correlation coefficient analysis assures that the low NDVI was mainly attributed to the low precipitation and water availability in the soils. This study provides valuable information in identifying the locations with the potential concern of drought and planning for immediate action of relief measures. Furthermore, this paper presents the results of the first attempt to apply a recently developed index, the Normalized Difference Latent Heat Index (NDLI), to monitor drought conditions. The results show that the NDLI has a high correlation with NDVI (r = 0.96), precipitation (r = 0.81), soil moisture (r = 0.73), and LST (r = −0.67). NDLI successfully captures the historical droughts and shows a notable correlation with the climatic variables. The analysis shows that using the radiances of green, red, and short wave infrared (SWIR), a simplified crop monitoring model with satisfactory accuracy and easiness can be developed.