Evaluation of deep learning algorithms for national scale landslide susceptibility mapping of Iran

The identification of landslide-prone areas is an essential step in landslide hazard assessment and mitigation of landslide-related losses.In this study,we applied two novel deep learning algorithms,the recurrent neural network(RNN)and convolutional neural network(CNN),for national-scale landslide susceptibility mapping of Iran.We prepared a dataset comprising 4069 historical landslide locations and 11 conditioning factors(altitude,slope degree,profile curvature,distance to river,aspect,plan curvature,distance to road,distance to fault,rainfall,geology and land-sue)to construct a geospatial database and divided the data into the training and the testing dataset.We then developed RNN and CNN algorithms to generate landslide susceptibility maps of Iran using the training dataset.We calculated the receiver operating characteristic(ROC)curve and used the area under the curve(AUC)for the quantitative evaluation of the landslide susceptibility maps using the testing dataset.Better performance in both the training and testing phases was provided by the RNN algorithm(AUC=0.88)than by the CNN algorithm(AUC=0.85).Finally,we calculated areas of susceptibility for each province and found that 6%and 14%of the land area of Iran is very highly and highly susceptible to future landslide events,respectively,with the highest susceptibility in Chaharmahal and Bakhtiari Province(33.8%).About 31%of cities of Iran are located in areas with high and very high landslide susceptibility.The results of the present study will be useful for the development of landslide hazard mitigation strategies.

Semantic and syntactic interoperability in online processing of big Earth observation data

The challenge of enabling syntactic and semantic interoperability for comprehensive and reproducible online processing of big Earth observation(EO)data is still unsolved.Supporting both types of interoperability is one of the requirements to efficiently extract valuable information from the large amount of available multi-temporal gridded data sets.The proposed system wraps world models,(semantic interoperability)into OGC Web Processing Services(syntactic interoperability)for semantic online analyses.World models describe spatio-temporal entities and their relationships in a formal way.The proposed system serves as enabler for(1)technical interoperability using a standardised interface to be used by all types of clients and(2)allowing experts from different domains to develop complex analyses together as collaborative effort.Users are connecting the world models online to the data,which are maintained in a centralised storage as 3D spatio-temporal data cubes.It allows also non-experts to extract valuable information from EO data because data management,low-level interactions or specific software issues can be ignored.We discuss the concept of the proposed system,provide a technical implementation example and describe three use cases for extracting changes from EO images and demonstrate the usability also for non-EO,gridded,multitemporal data sets(CORINE land cover).

Fuzzy Boundaries Between Post-Disaster Phases: The Case of L'Aquila, Italy

A number of indices have been developed for measuring vulnerability to disasters, but little attention has been paid to recovery indices. Post-disaster periods are usually divided into four phases. The terms established by the United Nations Development Programme for post-disaster phases—relief, early recovery, recovery, and development—are used in this article. This research examines the hypothesis that the boundaries between post-disaster recovery phases are fuzzy and should be defined by the progress achieved in the recovery process, rather than by the amount of time elapsed since the event. The methodology employed involved four steps: fieldwork, mapping,identification of indicators, and assessment. The case study area was the city of L'Aquila in the Abruzzo region of central Italy, which was struck by an earthquake in April2009. For each phase of the recovery process in L'Aquila a score was calculated based on the progress observed in2016, 7 years after the earthquake. The highest score went to the early recovery phase(14 points), followed by the recovery phase(13 points), the development phase(12points), and the relief phase(4 points). The results demonstrate the possibility of defining post-disaster recovery phases in an affected area based on measuring achievements through indicators rather than defining recovery phases in terms of elapsed time after a disaster.

Spatial risk assessment of opium poppy cultivation in Afghanistan: integrating environmental and socio-economic drivers

Recently the cultivation of opium poppy in Afghanistan reached unprecedented levels.It is agreed that the complex and coupled interactions of social,economic and environmental drivers are crucial for understanding the spatial and temporal dynamics of opium poppy cultivation in Afghanistan.In this context,we present an integrated risk concept,which considers environmental and socio-economic drivers of opium poppy cultivation.A set of spatially explicit indicators for the environmental suitability and socio-economic vulnerability was established and populated from a variety of databases.Subsequently,novel methods of modelling homogeneous and spatially explicit regions of opium poppy cultivation suitability,socio-economic vulnerability and risk are developed and applied.The risk assessment results demonstrate the complex nature of the illicit crops production in Afghanistan and prompt a more profound examination of the drivers of opium poppy cultivation in a spatial context.The study also confirms what has already been widely discussed in literature:that reasons for cultivation are spatially diverse and often distinct,meaning that any formulation of generalized explanations cannot be drawn without ignoring a more complex reality.Thus,an integrative spatial view of risk,which integrates the social dimension as well as environmental parameters,is required to better identify context-specific intervention measures.

Uses of online geoprocessing technology in analyses and case studies:a systematic analysis of literature

Interpreting spatial data to derive information is a core task in the field of Geographic Information Science and Technology.A logical step following the collection of data in online repositories is to provide geoprocessing technology for analysing data online.Online geoprocessing technology can be employed for providing a specified set of tools in a theme-specific platform,documenting a model or workflow and making it widely available,automating recurring tasks or offering simple tools to a large user group.This systematic analysis of literature evaluates how much available online geoprocessing tools are being used for answering questions in specific application contexts.An initial set of articles is derived from a keyword-based search in the database Scopus.This set of articles is manually filtered to identify applications of online geoprocessing tools.The analysis of application-related articles shows that virtually all applications require further development of tools.Experts outside the spatial information science field are still underrepresented regarding the use of this technology.The required adaptation of technology for user tasks is identified as major barrier for the wide use of online geoprocessing.Further research needs to assess user tasks and how online geoprocessing can provide the required functions in a useroriented manner.

GIS-based ordered weighted averaging and Dempster-Shafer methods for landslide susceptibility mapping in the Urmia Lake Basin, Iran

In this paper,GIS-based ordered weighted averaging(OWA)is applied to landslide susceptibility mapping(LSM)for the Urmia Lake Basin in northwest Iran.Nine landslide causal factors were used,whereby the respective parameters were extracted from an associated spatial database.These factors were evaluated,and then the respective factor weight and class weight were assigned to each of the associated factors using analytic hierarchy process(AHP).A landslide suscept-ibility map was produced based on OWA multicriteria decision analysis.In order to validate the result,the outcome of the OWA method was qualitatively evaluated based on an existing inventory of known landslides.Correspondingly,an uncertainty analysis was carried out using the Dempster-Shafer theory.Based on the results,very strong support was determined for the high susceptibility category of the landslide susceptibility map,while strong support was received for the areas with moderate susceptibility.In this paper,we discuss in which respect these results are useful for an improved understanding of the effectiveness of OWA in LSM,and how the landslide prediction map can be used for spatial planning tasks and for the mitigation of future hazards in the study area.

Monitoring long-term shoreline dynamics and human activities in the Hangzhou Bay,China,combining daytime and nighttime EO data

Shorelines are vulnerable to anthropogenic activities including urbanization,land reclamation and sediment loading.Shoreline changes may be a reflection of the degradation of coastal ecosystems because of human activities.Understanding the shoreline dynamics is,therefore,a topic of global concern.Earth observation data,such as multi-temporal satellite images,are an important resource for assessing changes in coastal ecosystems.In this research,we used Google Earth Engine(GEE)to monitor and map historical shoreline dynamics in the Hangzhou Bay in China where the Qiantang River flows into the East China Sea.Specifically,we aimed to capture and quantify both the spatial and temporal shoreline changes and to assess the link between anthropogenic activities and shoreline changes on the integrity of this coastal area.We implemented a Tasselled Cap analysis(TCA)on Landsat imagery from 1985 to 2018 in GEE to calculate the wetness coefficient.We then applied Otsu method for automatic image thresholding on the wetness coefficient to detect waterbodies and shoreline changes.Further,we adopted the nighttime light data from the Defense Meteorological Satellite Program’s Operational Linescan System(DMSP-OLS)from 1992 to 2013 as a proxy of human activities.The results show that in the hotspot areas,the shoreline has moved by more than 5 km in the last decades,accounting for approximately 900 km^(2) of land accretion.Within this area,the human activity,indicated by the intensity of nighttime light,increased significantly.The results of this work reveal the influence of human activities on the shoreline dynamics and can support policies that promote the sustainable use and conservation of coastal environments.Our methodology can be transferred and applied to other coastal zones in various regions and scaled up to larger areas.

Does DE need a C?A proposal for a DE curriculum

The vision of a digital earth(DE)is continuously evolving,and the next-generation infrastructures,platforms and applications are being implemented.In this article,we attempt to initiate a debate within the DE and with affine communities about‘why’a digital earth curriculum(DEC)is needed,‘how’it should be developed,and‘what’it could look like.It is impossible to do justice to the Herculean effort of DEC development without extensive consultations with the broader community.We propose a frame for the debate(what,why,and how of a DEC)and a rationale for and elements of a curriculum for educating the coming generations of digital natives and indicate possible realizations.We particularly argue that a DEC is not a déjàvu of classical research and training agendas of geographic information science,remote sensing,and similar fields by emphasizing its unique characteristics.

Processes and events in the center: a taxi trajectory-based approach to detecting traffic congestion and analyzing its causes

A novel approach is introduced for the detection of the location and direction of traffic congestion using GPS data from taxis.This approach uses a dynamic model that conceptualizes events,processes,and states.The states are the locations of the taxis,the processes are the motion of taxis,and the events are congestion.The model is implemented as a graph database,which represents the relationships between states,events,processes,and things(such as points of interest and road grid).Algorithms for constructing and updating the relationships and taxi behaviors dynamic retrieval method in Neo4j are presented and are used to demonstrate the capabilities in dynamic expression and reasoning.An implementation of Shanghai in 2015finally demonstrated the ability of congestion direction detection and the cause searching of traffic congestion.

Height estimation from single aerial imagery using contrastive learning based multi-scale refinement network

Height map estimation from a single aerial image plays a crucial role in localization,mapping,and 3D object detection.Deep convolutional neural networks have been used to predict height information from single-view remote sensing images,but these methods rely on large volumes of training data and often overlook geometric features present in orthographic images.To address these issues,this study proposes a gradient-based self-supervised learning network with momentum contrastive loss to extract geometric information from non-labeled images in the pretraining stage.Additionally,novel local implicit constraint layers are used at multiple decoding stages in the proposed supervised network to refine high-resolution features in height estimation.The structural-aware loss is also applied to improve the robustness of the network to positional shift and minor structural changes along the boundary area.Experimental evaluation on the ISPRS benchmark datasets shows that the proposed method outperforms other baseline networks,with minimum MAE and RMSE of 0.116 and 0.289 for the Vaihingen dataset and 0.077 and 0.481 for the Potsdam dataset,respectively.The proposed method also shows around threefold data efficiency improvements on the Potsdam dataset and domain generalization on the Enschede datasets.These results demonstrate the effectiveness of the proposed method in height map estimation from single-view remote sensing images.