Snow effects on alpine vegetation in the Qinghai-Tibetan Plateau

Understanding the relationships between snow and vegetation is important for interpretation of the responses of alpine ecosystems to climate changes.The Qinghai-Tibetan Plateau is regarded as an ideal area due to its undisturbed features with low population and relatively high snow cover.We used 500 m Moderate Resolution Imaging Spectroradiometer(MODIS)datasets during 2001–2010 to examine the snow–vegetation relationships,specifically,(1)the influence of snow melting date on vegetation green-up date and(2)the effects of snow cover duration on vegetation greenness.The results showed that the alpine vegetation responded strongly to snow phenology(i.e.,snow melting date and snow cover duration)over large areas of the Qinghai-Tibetan Plateau.Snow melting date and vegetation green-up date were significantly correlated(p<0.1)in 39.9% of meadow areas(accounting for 26.2% of vegetated areas)and 36.7% of steppe areas(28.1% of vegetated areas).Vegetation growth was influenced by different seasonal snow cover durations(SCDs)in different regions.Generally,the December–February and March–May SCDs played a significantly role in vegetation growth,both positively and negatively,depending on different water source regions.Snow’s positive impact on vegetation was larger than the negative impact.

A visual-textual fused approach to automated tagging of flood-related tweets during a flood event

In recent years,social media such as Twitter have received much attention as a new data source for rapid flood awareness.The timely response and large coverage provided by citizen sensors significantly compensate the limitations of non-timely remote sensing data and spatially isolated river gauges.However,automatic extraction of flood tweets from a massive tweets pool remains a challenge.Taking the Houston Flood in 2017 as a study case,this paper presents an automated flood tweets extraction approach by mining both visual and textual information a tweet contains.A CNN architecture was designed to classify the visual content of flood pictures during the Houston Flood.A sensitivity test was then applied to extract flood-sensitive keywords that were further used to refine the CNN classified results.A duplication test was finally performed to trim the database by removing the duplicated pictures to create the flood tweets pool for the flood event.The results indicated that coupling CNN classification results with flood-sensitive words in tweets allows a significant increase in precision while keeps the recall rate in a high level.The elimination of tweets containing duplicated pictures greatly contributes to higher spatio-temporal relevance to the flood.

Assessing 40 years of spatial dynamics and patterns in megacities along the Belt and Road region using satellite imagery

The Belt and Road(B&R)region,a vital area with historical,economic,cultural and political significance,has undergone rapid urbanization in the past several decades,especially in the form of urban expansion.In this study,20 megacities in the B&R region were selected to explore different spatiotemporal patterns of urban expansion.Object-oriented support vector machines(SVM),annual growth rate(AGR)models,and landscape metrics were employed to delineate the urban areas and characterize spatiotemporal characteristics and landscape patterns of these megacities during 1975–2015.All urban maps presented high overall accuracies(80.70%–95.90%)and overall Kappa coefficients(0.76–0.95).The study revealed that megacities in the B&R region have undergone different types of urban sprawl,mainly adopting a‘concentric circle’pattern in inland areas and a‘sector’pattern in coastal areas.Besides,six expansion modes were summarized according to the AGRs of individual megacities.Differences existed in megacities of the developing and developed countries and among five sub-regions.Moreover,‘dispersion,gathering,and re-dispersion’and‘coalescence’were two major landscape patterns of megacities in developing and developed countries.Results of this study can provide a scientific reference for urban planning and aid in sustainable development of local areas.

A 100 m population grid in the CONUS by disaggregating census data with open-source Microsoft building footprints

In the Big Data era,Earth observation is becoming a complex process integrating physical and social sectors.This study presents an approach to generating a 100 m population grid in the Contiguous United States(CONUS)by disaggregating the US cen-sus records using 125 million of building footprints released by Microsoft in 2018.Land-use data from the OpenStreetMap(OSM),a crowdsourcing platform,was applied to trim original footprints by removing the non-residential buildings.After trimming,several metrics of building measurements such as building size and build-ing count in a census tract were used as weighting scenarios,with which a dasymetric model was applied to disaggregate the American Community Survey(ACS)5-year estimates(2013-2017)into a 100 m population grid product.The results confirm that the OSM trimming process removes non-residential buildings and thus provides a better representation of population distribution within complicated urban fabrics.The building size in the census tract is found in the optimal weighting scenario.The product is 2.5Gb in size containing 800 million populated grids and is currently hosted by ESRI(http://arcg.is/19S4qK)for visualization.The data can be accessed via https://doi.org/10.7910/DVN/DLGP7Y.With the accel-erated acquisition of high-resolution spatial data,the product could be easily updated for spatial and temporal continuity.

Improved alpine grassland mapping in the Tibetan Plateau with MODIS time series: a phenology perspective

The Tibetan Plateau is primarily composed of alpine grasslands.Spatial distributions of alpine grasses,however,are not well documented in this remote,highly uninhabited region.Taking advantage of the frequently observed moderate resolution imaging spectroradiometer(MODIS)images(500-m,8-day)in 2010,this study extracted the phenological metrics of alpine grasses from the normalized difference vegetation index time series.With the Support Vector Machine,a multistep classification approach was developed to delineate alpine meadows,steppes,and desert grasses.The lakes,permanent snow,and barren/desert lands were also classified with a MODIS scene acquired in the peak growing season.With ground data collected in the field and aerial experiments in 2011,the overall accuracy reached 93%when alpine desert grasses and barren lands were not examined.In comparison with the recently published national vegetation map,the alpine grassland map in this study revealed smoother transition between alpine meadows and steppes,less alpine meadows in the southwest,and more barren/deserts in the high-cold Kunlun Mountain in the northeast.These variations better reflected climate control(e.g.precipitation)of different climatic divisions on alpine grasslands.The improved alpine grassland map could provide important base information about this cold region under the pressure of rapidly changing climate.

Identifying marsh dieback events from Landsat image series (1998–2018) with an Autoencoder in the NIWB estuary, South Carolina

This study reports an inventory of marsh dieback events from spatial and temporal perspectives in the North Inlet-Winyah Bay(NIWB)estuary,South Carolina(SC).Past studies in the Gulf/Atlantic coast states have reported acute marsh dieback events in which marsh rapidly browned and thinned,leaving stubble of dead stems or mudflat with damaged ecosystem services.Reported marsh dieback in SC,however,have been limited.This study identified all marsh dieback events in the estuary since 1998.With 20 annually collected Landsat images,the Normalized Difference Vegetation Index(NDVI)series was extracted.A Stacked Denoising Autoencoder neural network was developed to identify the NDVI anomalies on the trajectories.All marsh dieback patches were extracted,and their inter-annual changes were examined.Results showed a continuous,spatially variable multi-year dieback event in 1998–2005,which aligned with the reported dieback in the early 2000s from other states.The identified patches mostly returned to normal within one year while the phenomenon reoccurred in other areas of the estuary during the prolonged dieback period.This study presents the first attempt to explore long-term dieback dynamics in an estuary using satellite time series.It provides valuable information in documenting marsh healthiness and environmental resilience on SC coasts.

Identifying disaster related social media for rapid response:a visual-textual fused CNN architecture

In recent years,social media platforms have played a critical role in mitigation for a wide range of disasters.The highly up-to-date social responses and vast spatial coverage from millions of citizen sensors enable a timely and comprehensive disaster investigation.However,automatic retrieval of on-topic social media posts,especially considering both of their visual and textual information,remains a challenge.This paper presents an automatic approach to labeling on-topic social media posts using visual-textual fused features.Two convolutional neural networks(CNNs),Inception-V3 CNN and word embedded CNN,are applied to extract visual and textual features respectively from social media posts.Well-trained on our training sets,the extracted visual and textual features are further concatenated to form a fused feature to feed the final classification process.The results suggest that both CNNs perform remarkably well in learning visual and textual features.The fused feature proves that additional visual feature leads to more robustness compared with the situation where only textual feature is used.The on-topic posts,classified by their texts and pictures automatically,represent timely disaster documentation during an event.Coupling with rich spatial contexts when geotagged,social media could greatly aid in a variety of disaster mitigation approaches.