Shifts in the timing of spring phenology are a central feature of global change research. Long-term observations of plant phenology have been used to track vegetation responses to climate variability but are often limited to particular species and locations and may not represent synoptic patterns. Satellite remote sensing is instead used for continental to global monitoring. Although numerous methods exist to extract phenological timing, in particular start-of-spring (SOS), from time series of reflectance data, a comprehensive intercomparison and interpretation of SOS methods has not been conducted. Here, we assess 10 SOS methods for North America between 1982 and 2006. The techniques include consistent inputs from the 8km Global Inventory Modeling and Mapping Studies Advanced Very High Resolution Radiometer NDVIg dataset, independent data for snow cover, soil thaw, lake ice dynamics, spring streamflow timing, over 16000 individual measurements of ground-based phenology, and two temperature-driven models of spring phenology. Compared with an ensemble of the 10 SOS methods, we found that individual methods differed in average day-of-year estimates by ! 60 days and in standard deviation by ! 20 days. The ability of the satellite methods to retrieve SOS estimates was highest in northern latitudes and lowest in arid, tropical, and Mediterranean ecoregions. The ordinal rank of SOS methods varied geographically, as did the relationships between SOS estimates and the cryospheric/hydrologic metrics. Compared with ground observations, SOS estimates were more related to the first leaf and first flowers expanding phenological stages. We found no evidence for time trends in spring arrival from ground- or model-based data; using an ensemble estimate from two methods that were more closely related to ground observations than other methods, SOS

Intercomparison, interpretation, and assessment of spring phenology in North America estimated from remote sensing for 1982-2006 M I C H A E L A. W H I T E*, K I R S T E N M. DE BEURS w , K A M E L D I D A Nz, D AV I D W. I N O U Y E § ,

Object-based image classification for land-cover mapping purposes using remote-sensing imagery has attracted significant attention in recent years. Numerous studies conducted over the past decade have investigated a broad array of sensors, feature selection, classifiers, and other factors of interest. However, these research results have not yet been synthesized to provide coherent guidance on the effect of different supervised object-based land-cover classification processes. In this study, we first construct a database with 28 fields using qualitative and quantitative information extracted from 254 experimental cases described in 173 scientific papers. Second, the results of the meta-analysis are reported, including general characteristics of the studies (e.g., the geographic range of relevant institutes, preferred journals) and the relationships between factors of interest (e.g., spatial resolution and study area or optimal segmentation scale, accuracy and number of targeted classes), especially with respect to the classification accuracy of different sensors, segmentation scale, training set size, supervised classifiers, and land-cover types. Third, useful data on supervised object-based image classification are determined from the meta-analysis. For example, we find that supervised object-based classification is currently experiencing rapid advances, while development of the fuzzy technique is limited in the object-based framework. Furthermore, spatial resolution correlates with the optimal segmentation scale and study area, and Random Forest (RF) shows the best performance in object-based classification. The area-based accuracy assessment method can obtain stable classification performance, and indicates a strong correlation between accuracy and training set size, while the accuracy of the point-based method is likely to be unstable due to mixed objects. In addition, the overall accuracy benefits from higher spatial resolution images (e.g., unmanned aerial vehicle) or agricultural sites where it also correlates with the number of targeted classes. More than 95.6% of studies involve an area less than 300 ha, and the spatial resolution of images is predominantly between 0 and 2 m. Furthermore, we identify some methods that may advance supervised object-based image classification. For example, deep learning and type-2 fuzzy techniques may further improve classification accuracy. Lastly, scientists are strongly encouraged to report results of uncertainty studies to further explore the effects of varied factors on supervised object-based image classification.

A review of supervised object-based land-cover image classification

Urban land-use mapping using a deep convolutional neural network with high spatial resolution multispectral remote sensing imagery

Joint deep learning for land cover and land use classification

Urban land use information plays an essential role in a wide variety of urban planning and environmental monitoring processes. During the past few decades, with the rapid technological development of remote sensing RS, geographic information systems GIS and geospatial big data, numerous methods have been developed to identify urban land use at a fine scale. Points-of-interest POIs have been widely used to extract information pertaining to urban land use types and functional zones. However, it is difficult to quantify the relationship between spatial distributions of POIs and regional land use types due to a lack of reliable models. Previous methods may ignore abundant spatial features that can be extracted from POIs. In this study, we establish an innovative framework that detects urban land use distributions at the scale of traffic analysis zones TAZs by integrating Baidu POIs and a Word2Vec model. This framework was implemented using a Google open-source model of a deep-learning language in 2013. First, data for the Pearl River Delta PRD are transformed into a TAZ-POI corpus using a greedy algorithm by considering the spatial distributions of TAZs and inner POIs. Then, high-dimensional characteristic vectors of POIs and TAZs are extracted using the Word2Vec model. Finally, to validate the reliability of the POI/TAZ vectors, we implement a K-Means-based clustering model to analyze correlations between the POI/TAZ vectors and deploy TAZ vectors to identify urban land use types using a random forest algorithm RFA model. Compared with some state-of-the-art probabilistic topic models PTMs, the proposed method can efficiently obtain the highest accuracy OA = 0.8728, kappa = 0.8399. Moreover, the results can be used to help urban planners to monitor dynamic urban land use and evaluate the impact of urban planning schemes.

Sensing spatial distribution of urban land use by integrating points-of-interest and Google Word2Vec model

Mapping Annual Urban Evolution Process (2001–2018) at 250 m: A normalized multi-objective deep learning regression

ABSTRACT Due to the influence of the external atmospheric environment and the physical constraints of the sensors, it is difficult for existing medium spatial resolution sensors to produce intensive time-series images. The easy accessibility and similar sensor configuration of Landsat and Sentinel-2 data make them suitable for synthesizing time-series images. Currently, some deep learning-based studies have achieved significant success in multi-sensor fusion, but these deep-learning fusion networks only use single features that are not enough to produce intensive time-series images. Shallow features are easy to extract but have weak representation, while the deep network can extract abstract features with strong representation ability but faces the problem of gradient disappearance and model degradation. To address these problems, we propose a novel spatial-temporal-spectral integration model that can simultaneously fuse Landsat-7,8 and Sentinel-2 sensors. First, an enhanced residual dense network (ERDN) is proposed to improve Landsat’s four bands (Blue, Green, Red, and Near-infrared) to 10 m spatial resolution. ERDN’s residual dense structure utilizes abundant shallow features (i.e. texture and spectral information) and deep features (i.e. angles of view and aspect ratios of objects) to reconstruct spatial structures. At the same time, the introduced high-resolution images can provide reliable spatial auxiliary information for the missing image parts. Second, we employ a time-series-based reflectance adjustment (TRA) method to reduce the reflectance differences between Landsat and Sentinel-2 images. The fusion results indicate that our fusion framework can not only fill the gap caused by the Landsat-7 scan-line corrector (SLC) failure but also restore more spatial details than previous methods. More importantly, it can predict tiny reflectance changes in land cover. Overall, our study can produce continuous reflection observations with a higher time density and provides important data guarantee for extracting dynamic changes in land coverages.

Fusing Landsat-7, Landsat-8 and Sentinel-2 surface reflectance to generate dense time series images with 10m spatial resolution

Naive Geography, intelligent geographical information systems (GIS), and spatial data mining especially from social media all rely on natural-language spatial relations (NLSR) terms to incorporate commonsense spatial knowledge into conventional GIS and to enhance the semantic interoperability of spatial information in social media data. Yet, the inherent fuzziness of NLSR terms makes them challenging to interpret. This study proposes to interpret the fuzzy semantics of NLSR terms using the fuzzy random forest (FRF) algorithm. Based on a large number of fuzzy samples acquired by transforming a set of crisp samples with the random forest algorithm, two FRF models with different membership assembling strategies are trained to obtain the fuzzy interpretation of three line-region geometric representations using 69 NLSR terms. Experimental results demonstrate that the two FRF models achieve good accuracy in interpreting line-region geometric representations using fuzzy NLSR terms. In addition, fuzzy classification of FRF can interpret the fuzzy semantics of NLSR terms more fully than their crisp counterparts.

Interpreting the Fuzzy Semantics of Natural-Language Spatial Relation Terms with the Fuzzy Random Forest Algorithm

Land covers provide essential information for understanding and detecting ecosystem, resources, and environmental dynamics. However, they are generally mapped at coarser temporal scales to study th...

Intra-annual land cover mapping and dynamics analysis with dense satellite image time series: a spatiotemporal cube based spatiotemporal contextual method

The spectral uncertainty refers to the diversity and variations of spectral characteristics within a single geographic object or across different objects of the same class. Usually, existing methods represent the spectral characteristics as precise single-valued curves. Thus, the spectral variations cannot be modeled, which further restricts the analysis and classification performance of remote sensing images. On the other hand, unsupervised methods have poor performance in classification and modeling uncertainty, while supervised methods need a large number of samples with high quality. Fuzzy semi-supervised clustering (FSSC) methods achieve a high accuracy with limited labelled samples. Thus, currently, FSSC methods attract more and more attention. This paper proposes a novel method to model the spectral uncertainty for very-high-resolution (VHR) images based on interval type-2 fuzzy sets (IT2 FSs), namely the hierarchical semi-supervising and weighted interval type-2 fuzzy c-means for objects (hierarchical SSW-IT2FCM-O) clustering method. In this method, the VHR image is segmented into image objects to reduce spectral uncertainty within objects. Spectral values, spectral indices and textures were weighted for object-based image classification. To further reduce spectral uncertainty across different objects of the same class, the spectral characteristics of land cover types were represented as banded curves with certain widths instead of precise single-valued spectral curves. The experimental results show that the banded spectral curves produced by the hierarchical SSW-IT2FCM-O can effectively model the spectral uncertainty of geographic objects. From the perspective of classification, four typical validity indices along with the confusion matrix and kappa coefficient were used to test the effectiveness of the hierarchical SSW-IT2FCM-O method, and these indices show that the presented method SSW-IT2FCM-O has greater classification accuracy than the existing FSSC methods and, more importantly, it requires smaller training samples than the existing methods.

Modelling the Spectral Uncertainty of Geographic Features in High-Resolution Remote Sensing Images: Semi-Supervising and Weighted Interval Type-2 Fuzzy C-Means Clustering

Xiuyuan Zhang

Papers

Mapping Annual Urban Evolution Process (2001–2018) at 250 m: A normalized multi-objective deep learning regression

Fusing Landsat-7, Landsat-8 and Sentinel-2 surface reflectance to generate dense time series images with 10m spatial resolution

Interpreting the Fuzzy Semantics of Natural-Language Spatial Relation Terms with the Fuzzy Random Forest Algorithm

Intra-annual land cover mapping and dynamics analysis with dense satellite image time series: a spatiotemporal cube based spatiotemporal contextual method

Modelling the Spectral Uncertainty of Geographic Features in High-Resolution Remote Sensing Images: Semi-Supervising and Weighted Interval Type-2 Fuzzy C-Means Clustering