Search

• A deep learning algorithm is used to build a comprehensive drought monitoring model. • Multi-source remote sensing data is processed as input data. • The comprehensive drought model has good applicability in the monitoring of meteorological drought and agricultural drought. • The model successfully monitored a drought process in Henan Province, China. • This study provides a new method for the comprehensive assessment of regional drought. Drought is a popular scientific issue in global climate change research. Accurate monitoring of drought has important implications for the sustainable development of regional agriculture in the context of increasingly complex global climate change. Deep learning is a widely used technique in the field of artificial intelligence. However, ongoing on drought monitoring using deep learning is relatively scarce. In this paper, the various hazard factors in drought development were comprehensively considered based on satellite data including Moderate Resolution Imaging Spectroradiometer (MODIS) and tropical rainfall measuring mission (TRMM) as multi-source remote sensing data. By using the deep learning technique, a comprehensive drought monitoring model was constructed and tested in Henan Province of China as an example. The results showed that the comprehensive drought model has good applicability in the monitoring of meteorological drought and agricultural drought. There was a significant positive correlation between the drought indicators of the model output and the comprehensive meteorological drought index (CI) measured at the site scale. The consistency rate of the drought grade of the two models was 85.6% and 79.8% for the training set and the test set, respectively. The correlation coefficient between the drought index of the model and the standard precipitation evapotranspiration index (SPEI) was between 0.772 and 0.910 (P < 0.01), which indicated a strong level of significance. The correlation coefficient between the drought index of the model and the soil relative moisture at a 10 cm depth was greater than 0.550 (P < 0.01), and there was a good correlation between them. This study provides a new method for the comprehensive assessment of regional drought. [ABSTRACT FROM AUTHOR]

We present and evaluate a quantitative method for delineation of ecophysiographic regions throughout the entire terrestrial landmass. The method uses the new pattern-based segmentation technique which attempts to emulate the qualitative, weight-of-evidence approach to a delineation of ecoregions in a computer code. An ecophysiographic region is characterized by homogeneous physiography defined by the cohesiveness of patterns of four variables: land cover, soils, landforms, and climatic patterns. Homogeneous physiography is a necessary but not sufficient condition for a region to be an ecoregion, thus machine delineation of ecophysiographic regions is the first, important step toward global ecoregionalization. In this paper, we focus on the first-order approximation of the proposed method – delineation on the basis of the patterns of the land cover alone. We justify this approximation by the existence of significant spatial associations between various physiographic variables. Resulting ecophysiographic regionalization (ECOR) is shown to be more physiographically homogeneous than existing global ecoregionalizations (Terrestrial Ecoregions of the World (TEW) and Bailey's Ecoregions of the Continents (BEC)). The presented quantitative method has an advantage of being transparent and objective. It can be verified, easily updated, modified and customized for specific applications. Each region in ECOR contains detailed, SQL-searchable information about physiographic patterns within it. It also has a computer-generated label. To give a sense of how ECOR compares to TEW and, in the U.S., to EPA Level III ecoregions, we contrast these different delineations using two specific sites as examples. We conclude that ECOR yields regionalization somewhat similar to EPA level III ecoregions, but for the entire world, and by automatic means. [ABSTRACT FROM AUTHOR]

Change detection in satellite images is a key concern of the Earth Observation field for environmental and climate change monitoring. Satellite images also provide important clues to both the past and present surface conditions of other planets, which cannot be validated on the ground. With the volume of satellite imagery continuing to grow, the inadequacy of computerised solutions to manage and process imagery to the required professional standard is of critical concern. Whilst studies find the crowd sourcing approach suitable for the counting of impact craters in single images, images of higher resolution contain a much wider range of features, and the performance of novices in identifying more complex features and detecting change, remains unknown. This paper presents a first step towards understanding whether novices can identify and annotate changes in different geomorphological features. A website was developed to enable visitors to flick between two images of the same location on Mars taken at different times and classify 1) if a surface feature changed and if so, 2) what feature had changed from a pre-defined list of six. Planetary scientists provided “expert” data against which classifications made by novices could be compared when the project subsequently went public. Whilst no significant difference was found in images identified with surface changes by expert and novices, results exhibited differences in consensus within and between experts and novices when asked to classify the type of change. Experts demonstrated higher levels of agreement in classification of changes as dust devil tracks, slope streaks and impact craters than other features, whilst the consensus of novices was consistent across feature types; furthermore, the level of consensus amongst regardless of feature type. These trends are secondary to the low levels of consensus found, regardless of feature type or classifier expertise. These findings demand the attention of researchers who want to use crowd-sourcing for similar scientific purposes, particularly for the supervised training of computer algorithms, and inform the scope and design of future projects. [ABSTRACT FROM AUTHOR]

Image classification from remote sensing is becoming increasingly urgent for monitoring environmental changes. Exploring effective algorithms to increase classification accuracy is critical. This paper explores the use of multispectral HJ1B and ALOS (Advanced Land Observing Satellite) PALSAR L-band (Phased Array type L-band Synthetic Aperture Radar) for land cover classification using learning-based algorithms. Pixel-based and object-based image analysis approaches for classifying HJ1B data and the HJ1B and ALOS/PALSAR fused-images were compared using two machine learning algorithms, support vector machine (SVM) and random forest (RF), to test which algorithm can achieve the best classification accuracy in arid and semiarid regions. The overall accuracies of the pixel-based (Fused data: 79.0%; HJ1B data: 81.46%) and object-based classifications (Fused data: 80.0%; HJ1B data: 76.9%) were relatively close when using the SVM classifier. The pixel-based classification achieved a high overall accuracy (85.5%) using the RF algorithm for classifying the fused data, whereas the RF classifier using the object-based image analysis produced a lower overall accuracy (70.2%). The study demonstrates that the pixel-based classification utilized fewer variables and performed relatively better than the object-based classification using HJ1B imagery and the fused data. Generally, the integration of the HJ1B and ALOS/PALSAR imagery can improve the overall accuracy of 5.7% using the pixel-based image analysis and RF classifier. [ABSTRACT FROM AUTHOR]

Timely and accurate monitoring of the onset and evolution of drought in China are important to reduce losses from drought. The Integrated Surface Drought Index (ISDI) which originally established in mideast China shows a large potential for real-time regional drought monitoring. However, ISDI is still at the developmental stage, and the applicability of the index requires further examination especially for China with vast area, climatic conditions, complex topography, and land cover. Furthermore, ISDI model depends on the historical training data corresponding to the study area. ISDI application in China must be remodeled using the historical training data over China. In this paper, we remodeled ISDI over China based on previous work and evaluated its capability for near real-time drought monitoring. Using the Palmer Drought Severity Index (PDSI) as a dependent variable, ISDI integrates climate-based drought indices, satellite-based Vegetation Index (VI) and land surface temperature (LST) with other biophysical and elevation data to produce a 1-km regional drought condition map at 16-day intervals. Strong relationships were determined between the calculated ISDI and PDSI for spring, summer and autumn, and all of the correlation coefficients exceeded 0.8. The initial ISDI results demonstrated a good performance for monitoring droughts in southwestern China from 2009 to 2010, high temperatures and droughts in southern China in 2013, and floods in northeastern China in 2013. The higher spatial resolution and near real-time capability of ISDI can provide important inputs for drought management and mitigation in China. [ABSTRACT FROM AUTHOR]

Forest fires are one of the most important causes of environmental alteration in Mediterranean countries. Discrimination of different degrees of burn severity is critical for improving management of fire-affected areas. This paper aims to evaluate the usefulness of land surface temperature (LST) as potential indicator of burn severity. We used a large convention-dominated wildfire, which occurred on 19–21 September, 2012 in Northwestern Spain. From this area, a 1-year series of six LST images were generated from Landsat 7 Enhanced Thematic Mapper (ETM+) data using a single channel algorithm. Further, the Composite Burn Index (CBI) was measured in 111 field plots to identify the burn severity level (low, moderate, and high). Evaluation of the potential relationship between post-fire LST and ground measured CBI was performed by both correlation analysis and regression models. Correlation coefficients were higher in the immediate post-fire LST images, but decreased during the fall of 2012 and increased again with a second maximum value in summer, 2013. A linear regression model between post-fire LST and CBI allowed us to represent spatially predicted CBI ( R -squared adj > 85%). After performing an analysis of variance (ANOVA) between post-fire LST and CBI, a Fisher's least significant difference test determined that two burn severity levels (low-moderate and high) could be statistically distinguished. The identification of such burn severity levels is sufficient and useful to forest managers. We conclude that summer post-fire LST from moderate resolution satellite data may be considered as a valuable indicator of burn severity for large fires in Mediterranean forest ecosytems. [ABSTRACT FROM AUTHOR]

This paper combines participatory activities (PA) with remote sensing analysis into an integrated methodology to describe and explain land-cover changes. A remote watershed on Mindanao (Philippines) is used to showcase the approach, which hypothesizes that the accuracy of expert knowledge gained from remote sensing techniques can be further enhanced by inputs from vernacular knowledge when attempting to understand complex land mosaics and past land-use changes. Six participatory sessions based on focus-group discussions were conducted. These were enhanced by community-based land-use mapping, resulting in a final total of 21 participatory land-use maps (PLUMs) co-produced by a sample of stakeholders with different sociocultural and ecological perspectives. In parallel, seven satellite images (Landsat MSS, Landsat TM, Landsat ETM+, and SPOT4) were classified following standard techniques and provided snapshots for the years 1976, 1996, and 2010. Local knowledge and collective memory contributed to define and qualify relevant land-use classes. This also provided information about what had caused the land-use changes in the past. Results show that combining PA with remote-sensing analysis provides a unique understanding of land-cover change because the two methods complement and validate one another. Substantive qualitative information regarding the chronology of land-cover change was obtained in a short amount of time across an area poorly covered by scientific literature. The remote sensing techniques contributed to test and to quantify verbal reports of land-use and land-cover change by stakeholders. We conclude that the method is particularly relevant to data-poor areas or conflict zones where rapid reconnaissance work is the only available option. It provides a preliminary but accurate baseline for capturing land changes and for reporting their causes and consequences. A discussion of the main challenges encountered (i.e. how to combine different systems of knowledge), and options for further methodological improvements, are also provided. [ABSTRACT FROM AUTHOR]

Abstract: This paper evaluates the usefulness of the hyperspectral imager (HSI) onboard Chinese HJ-1-A small satellite in vegetation mapping. Fractional vegetation cover (FVC) is an important surface microclimate parameter for characterizing land surface vegetation cover as well as the most effective indicator for assessing desertification and crop growth condition. The HJ-1/HSI data were used to calculate the narrow band vegetation index by using the in situ plot FVC data, which was then applied in sub-pixel de-composition model for the FVC estimation, namely the dimidiate pixel model. The FVC information in the Shihezi Area, Xinjiang, China was retrieved based on the dimidiate pixel model. Cross-checked with the in situ measured FVC data, a correlation coefficient square of 0.86, and the root mean square error of 10.9% is statistically achieved. The verification indicates that the FVC result retrieved from the HJ-1/HSI data is well correlated with the in situ measurements, demonstrating that the HJ-1/HSI data are promising for studying the potential impacts of global climate change on the arid and semi-arid landscapes. [Copyright &y& Elsevier]

Abstract: High resolution digital airborne imagery offers unprecedented opportunities for observation and monitoring of vegetation, providing the potential to identify, locate and track individual vegetation objects over time. Analytical tools are required to quantify relevant information. In this paper, locations of trees over a large area of native woodland vegetation were identified using morphological image analysis techniques. Methods of spatial point process statistics were then applied to estimate the spatially-varying tree death risk, and to show that it is significantly non-uniform. [Tree deaths over the area were detected in our previous work (Wallace et al., 2008).] The study area is a major source of ground water for the city of Perth, and the work was motivated by the need to understand and quantify vegetation changes in the context of water extraction and drying climate. The influence of hydrological variables on tree death risk was investigated using spatial statistics (graphical exploratory methods, spatial point pattern modelling and diagnostics). [Copyright &y& Elsevier]

Abstract: In this paper we investigated if and how a signature of climate control on vegetation growth can be individualized at regional scale using time series of SPOT-VEGETATION NDVI and ECMWF meteorological data. Twelve regions characterized by dominant and stable cropland or grassland covers were selected in Europe and Africa. Our results show that the relationship between NDVI and meteorological parameters is highly complex and significantly vary trough the phenological cycle of the plants. Hence, interactions between vegetation dynamics and climate variability must be studied at a smaller time scale in order to identify properly the limiting factors to vegetation growth. Using NDVI metrics, vegetative phases (from green-up to maximum NDVI) and reproductive phases (from maximum NDVI to maturity) were identified for each region. Cross-correlation analysis revealed that, in most of the cases, the best scores of Pearson''s r are obtained when we considered the vegetative phase (from green-up to maximum of NDVI) and the reproductive phase (from maximum of NDVI to maturity) separately. We also showed that climatic constraints identified using yearly proxies of climate and vegetation do not depict correctly or completely the climate control on vegetation development. In that sense the complexity of the climate-vegetation relationship, which is spatially and temporally variable, is well underlined in this study. [Copyright &y& Elsevier]

Abstract: The analysis and forecasting of extreme climatic events has become increasingly relevant to plan effective financial and food-related interventions in third-world countries. Natural disasters and climate change, both large and small scale, have a great impact on non-industrialized populations who rely exclusively on activities such as crop production, fishing, and similar livelihood activities. It is important to identify the extent of the areas prone to severe drought conditions in order to study the possible consequences of the drought on annual crop production. In this paper, we aim to identify such areas within the South Tigray zone, Ethiopia, using a transformation of the Normalized Difference Vegetation Index (NDVI) called Absolute Difference NDVI (ADVI). Negative NDVI shifts from the historical average can generally be linked to a reduction in the vigor of local vegetation. Drought is more likely to increase in areas where negative shifts occur more frequently and with high magnitude, making it possible to spot critical situations. We propose a new methodology for the assessment of drought risk in areas where crop production represents a primary source of livelihood for its inhabitants. We estimate ADVI return levels pixel per pixel by fitting extreme value models to independent monthly minima. The study is conducted using SPOT-Vegetation (VGT) ten-day composite (S10) images from April 1998 to March 2009. In all short-term and long-term predictions, we found that central and southern areas of the South Tigray zone are prone to a higher drought risk compared to other areas. [Copyright &y& Elsevier]

Abstract: Agricultural development under climatic variations has resulted in substantial loss of marshes in the West Songnen Plain in the past decades. In this paper, the shrinkage and fragmentation process of marshes and its possible causes in the West Songnen Plain from 1954 to 2008 were explored using historical topographic maps and remote sensing data. Results indicated that the West Songnen Plain underwent considerable shrinkage and fragmentation of marshes in that same period. Marshes occupied 6404km2 in 1954, but this area has decreased by 74% in the past 54 years. The average annual decrease rate of marshes was 88km2 per year. Meanwhile, the number of marsh patches decreased from 1411 to 514, and the mean patch size decreased from 454 to 320ha. Cropland and salinized wasteland were the two main land use types into which marshes were converted. During the same period, grassland decreased by 54%, cropland increased by 22%, and salinized wasteland expanded by 612%. A significant increase in air temperature and index of dryness was found in the study region, along with decreased precipitation, thereby affecting the marsh systems through the changing hydrological regimes. On the other hand, population, gross domestic product, and livestock number increased considerably as marshes shrank and became fragmented. Governmental policy changes played a key role in land use transformations in the study region. [Copyright &y& Elsevier]

Abstract: With the development of global changes, researchers from all over the world increasingly pay attention to drought detection, and severe droughts that may have resulted from climate change. In this paper, spatial and temporal variability of drought is evaluated based on precipitation data and remotely sensed images. The standard precipitation index (SPI) and vegetation condition index (VCI) are used to evaluate the spatial and temporal characteristics of meteorological and vegetative drought in Tigray, Northern Ethiopia. Based on the drought critical values of SPI and VCI defining drought, the spatial and temporal extent of droughts in the study area is established. We processed 396 decadal images in order to produce the multi-temporal VCI drought maps. The results of the SPI and VCI analysis reveal that the eastern and southern zones of the study region suffered a recurrent cycle of drought over the last decade. Results further show that there is a time lag between the period of the peak VCI and precipitation values obtained from the meteorological stations across the study area. A significant agreement was observed between VCI values with the current plus last two-months of precipitation. The study demonstrates the utility of the vegetation condition index in semi-arid and arid regions. [Copyright &y& Elsevier]

Abstract: Environmental issues such as air, groundwater pollution and climate change are frequently studied at spatial scales that cross boundaries between political and administrative regions. It is common for different administrations to employ different data collection methods. If these differences are not taken into account in spatial interpolation procedures then biases may appear and cause unrealistic results. The resulting maps may show misleading patterns and lead to wrong interpretations. Also, errors will propagate when these maps are used as input to environmental process models. In this paper we present and apply a geostatistical model that generalizes the universal kriging model such that it can handle heterogeneous data sources. The associated best linear unbiased estimation and prediction (BLUE and BLUP) equations are presented and it is shown that these lead to harmonized maps from which estimated biases are removed. The methodology is illustrated with an example of country bias removal in a radioactivity exposure assessment for four European countries. The application also addresses multicollinearity problems in data harmonization, which arise when both artificial bias factors and natural drifts are present and cannot easily be distinguished. Solutions for handling multicollinearity are suggested and directions for further investigations proposed. [Copyright &y& Elsevier]

Abstract: Terrestrial ecosystems provide a number of vital services for people and society, such as food, fibre, water resources, carbon sequestration, and recreation. The future capability of ecosystems to provide these services is determined by changes in socio-economic factors, land use, atmospheric composition, and climate. Most impact assessments do not quantify the vulnerability of ecosystems and ecosystem services under such environmental change. They cannot answer important policy-relevant questions such as ‘Which are the main regions or sectors that are most vulnerable to global change?’ ‘How do the vulnerabilities of two regions compare?’ ‘Which scenario is the least harmful for a sector?’ This paper describes a new approach to vulnerability assessment developed by the Advanced Terrestrial Ecosystem Analysis and Modelling (ATEAM) project. Different ecosystem models, covering biodiversity, agriculture, forestry, hydrology, and carbon sequestration are fed with the same Intergovernmental Panel on Climate Change (IPCC) scenarios based on the Special Report on Emissions Scenarios (SRES). Each model gives insights into specific ecosystems, as in traditional impact assessments. Moreover, by integrating the results in a vulnerability assessment, the policy-relevant questions listed above can also be addressed. A statistically derived European environmental stratification forms a key element in the vulnerability assessment. By linking it to other quantitative environmental stratifications, comparisons can be made using data from different assessments and spatial scales. [Copyright &y& Elsevier]

Abstract: This paper addresses a critical need to provide a better quantitative understanding of how the Sudano-Sahelian environments actually been changing under the combined impacts of climate variability and the increasing pressure of human activity. Using Corona, Landsat and SPOT satellite images of three areas (90–250km2) along the climatic gradient of a large catchment in Mali, significant land-cover changes since the 1960s were identified through visual interpretation of images following a common classification scheme. The pattern and trajectory of changes differed markedly between the three areas studied. Overall, the 40-year trends indicate: (i) in the Sahelian area, a steady increase in croplands and erosional surfaces with sparse vegetation and a corresponding drastic reduction in woody covers; (ii) in the Sudano-Sahelian area, a large increase in croplands and a moderate reduction in woody covers; (iii) in the Sudanian area, agricultural extension, deforestation, but also reforestation and land rehabilitation, due to alternating periods of exploitation and recolonization by natural vegetation. These patterns and dynamics can be partially explained by the differences in demographic pressure between the three areas. They also highlight differences in response to anthropogenic and climate forcings depending on the areas’ respective climatic and environmental endowments. This study is a first step towards an in-depth analysis of the various forces and processes driving these changes and the formulation of prospective environmental scenarios for the catchment in line with hydrological studies. [Copyright &y& Elsevier]