Search

Effective geographic environment observation planning is the key to obtain disaster monitoring and warning information. The previous researches can only make observation plans for a single disaster at some specific stages. They are difficult to apply to the dynamic evolution of the disaster chain. Timely and comprehensive geographic environment observation planning is urgently needed to provide high-value monitoring data for the identification and response of secondary disaster chains. Event logic graph (ELG) shows great potential in evolutionary law expression and chain event reasoning. Therefore, this study proposed an observation ELG (OELG), in which events and their logical relationships are modeled as nodes and edges to express the occurrence and development motivation of observation events. The disaster chain observation planning can be transformed into the reasoning of potential continuous observation events. Subsequently, an OELG-based geographic environment observation planning framework was proposed, which realizes the construction, instantiation, and plan reasoning of OELG. The observation planning experiment was carried out taking the flood disaster chain that occurred in Beijing, China and Nordrhein-Westfalen, Germany as examples. The results show that OELG can generate disaster chain observation plan more timely, comprehensively, and continuously than other models, thus providing support for disaster chain risk monitoring and emergency response.

Significant advancements in Earth Observation (EO) technologies, encompassing global remote sensing and environment sensor networks, have greatly progressed the field of earth science. The management of EO sensors is crucial in collecting effective and changing EO data in real-time. Over the past few decades, Sensor Management (SM) and Multi-Sensor Management (MSM) have been extensively applied to EO research and reviewed in previous studies. The demands for EO have become highly complex with the advent of the EO sensor web era, necessitating Multi-Sensor Integration Management (MSIM), which is an advanced development of MSM. The concept of MSIM and its methods have been discussed worldwide, and the prototypes have exhibited remarkable potential for EO applications. However, MSIM is yet to be reviewed for a long time. This work provides a detailed overview of the emergence of MSIM and specifies its four key methods. This work also examines the typical MSIM prototypes and applications in EO. Then, this work identifies four future directions of MSIM in EO research. This review concludes that MSIM has emerged as a novel and indispensable sensor management paradigm set to play a significant role in the advancement of earth science research and practical applications in the future.

Accurate and continuous crop phenology information at a regional scale is important for agronomic management and yield estimation. However, detecting continuous crop phenology remains challenging due to the low sensitivity of remote sensing signals to certain phenological stages and the limited of availability remote sensing images. Therefore, this study developed a layered strategy to detect continuous crop phenology. First, a novel Phenology Separability Index (PSI) is established to select features from the Gaussian probability density distribution. PSI quantifies the capability of optical vegetation indexes (VIs), Synthetic Aperture Radar (SAR) signals, and meteorological factors to distinguish between various phenological stages. Then, the multi-temporal sample is established to enhance training sample representation and quantity. Finally, a random forest model is trained using features extracted from multi-temporal samples to improve detection accuracy. This model effectively reduces phenological stage confusion due to redundant features and limited samples. In addition, this study validated its extensibility by mapping crop phenology in the cities of Acheng, Zhaozhou, Lishu, and Buxin and assessed its uncertainty using the Sobol approach. Results indicated that growing degree day has the highest separability among meteorological factors, surpassing both SAR singles and optical VIs. Moreover, the proposed layered strategy was robust, explaining 96% of spatial variation in crop phenology at the regional scale. The accuracy of the layered strategy method (total RMSE = 8.74 days) surpassed that of the multi-temporal sample method (total RMSE = 15.76 days) and the traditional method with a single-temporal sample (total RMSE = 17.21 days). In addition, this study indicated that optical VIs are prone to confuse with the early or late phenological stage of corn, whereas SAR singles are highly sensitive to jointing date.

Accurate, timely, and fine-resolution crop phenology is essential for determining the optimal timing of agronomic management practices supporting precision agriculture and food security. Synthetic Aperture Radar (SAR) methods, unaffected by cloud occlusion, have been widely applied in monitoring maize phenology. Nonetheless, their reliance on manual threshold settings, which depend on the user’s expertise, limits their applicability. Furthermore, the neglect of SAR’s potential for monitoring other phenological periods (e.g., seven-leaves date (V7), jointing date (JD), tassel date (TD), and milky date (MID)) hinders their robustness, particularly for regional-scale applications. To address these issues, this study used an adaptive dynamic threshold to evaluate the ability of the Sentinel-1 cross-polarization ratio (CR) in detecting the three-leaves date (V3), V7, JD, TD, MID, and maturity date (MD) of maize. We analyzed the effect of incidence angle, precipitation, and wind speed on Sentinel-1 features to identify the optimal feature for time series fitting. Then, we employed linear regression to determine the optimal threshold and developed an adaptive dynamic threshold for phenology detection. This approach effectively mitigated the speckle noise of Sentinel-1 and minimized artificial interference caused by customary conventional thresholds. Finally, we mapped phenology across 8.3 million ha in Heilongjiang Province. The results indicated that the approach has a higher ability to detect JD (RMSE = 11.10 d), MID (RMSE = 10.31 d), and MD (RMSE = 9.41 d) than that of V3 (RMSE = 32.07 d), V7 (RMSE = 56.37 d), and TD (RMSE = 43.33 d) in Sentinel-1. Compared with Sentinel-2, the average RMSE of JD, MID, and MD decreased by 4.14%, 35.28%, and 26.48%. Moreover, when compared to different thresholds, the adaptive dynamic threshold can quickly determine the optimal threshold for detecting each phenological stage. CR is least affected by incident angle, precipitation, and wind speed, effectively suppressing noise to reflect phenological development better. This approach supports the rapid and feasible mapping of maize phenology across broad spatial regions with a few samples.

The optimal collaborative observation planning of Earth observation (EO) sensors is essential for disaster monitoring. This goal requires comprehensively characterizing the observation capability associations among these sensors. Previous studies only solved the static binary-associated observation capability for the optimized collaborative planning of two-sensor combinations, while the dynamic N-ary-associated observation capability that supports the optimized collaborative planning of N-sensor combination remained to be addressed. This study proposes a space–time composite observation capability association graph (OCAG) model, where its constituent sensors and association relations are modeled as nodes and edges, respectively, to address this gap. The proposed model divides an observation scenario into several states, with each state utilizing an OCAG to characterize the association relations, especially the N-ary association relations, among the EO sensors. The N-ary association relations can function as optimized observation plans to satisfy various observation requirements. A flood observation planning experiment was conducted in Hubei, China. Experimental results indicate that all association relations, especially the N-ary ones, can be solved at multiple space–time snapshots, enabling sensor planners to comprehensively and optimally collaborate EO sensors for flood observation.

A comprehensive, accurate, and timely expression of earth observation (EO) tasks is the primary prerequisite for the response to and the emergency monitoring of disasters, especially floods. However, the existing information model does not fully satisfy the demand for a fine-grain observation expression of EO task, which results in the absence of task process management. The current study proposed an EO task representation model based on meta-object facility to address this problem. The model not only describes the static information of a task, but it also defines the dynamics of an observation task by introducing a functional metamodel. This metamodel describes the full life cycle of a task; it comprises five process methods: birth, separation, combination, updating, and extinction. An earth observation task modeling and management prototype system (EO-TMMS) for conducting a remote sensing satellite sensor observation task representation experiment on flooding was developed. In accordance with the results, the proposed model can describe various EO tasks demands and the full life cycle process of an EO task. Compared with other typical observation task information models, the proposed model satisfies the dynamic and fine-grain process representation of EO tasks, which can improve the efficiency of EO sensor utilization.

Remote sensing imagery typically comprises successive background contexts and complex objects. Global average pooling is a popular choice to connect the convolutional and fully connected (FC) layers for the deep convolution network. This article equips the networks with another pooling strategy, namely the deep object-centric pooling (DOCP), to pool convolutional features considering the location of an object within the scene image. The proposed DOCP network structure consists of the following two steps: inferring object's location and separately pooling the foreground and background features to generate an object-level representation. Specifically, a spatial context module is presented to learn the location of the object of interest in the scene image. Then, the convolutional feature maps are pooled separately in the foreground and background of the object. Finally, the FC layer concatenates these pooled features and is followed by a batch normalization layer, a dropout layer, and a softmax layer. Two challenging datasets are employed to validate our approach. The experimental results demonstrate that the proposed DOCP-net can outperform the corresponding pooling methods and achieve a better classification performance than other pretrained convolutional neural network-based scene classification methods.

Most existing deep learning-based methods use feature maps extracted from convolutional neural networks (CNNs) for classification and detection of high-resolution remote sensing images (HRSIs). However, directly applying these features to classification and object detection in HRSI is problematic because of rotational variations. In this article, we design networks using the polycentric circle pooling (PCP) strategy to alleviate the abovementioned problem. The PCP network (PCP-net) structure can generate a fixed-length representation for different input image sizes and encode rotation-invariant information. With these advantages, PCP-net should in general improve the CNN-based HRSI classification methods. Specifically, on the basis of the concentric circle pooling network structure, we improve the structure using multiple concentric circle centers to generate more robust rotation-invariant information. Using two challenging HRSI scene datasets, we prove that PCP-net improves the accuracy of CNN architectures for a scene classification tasks. PCP-net can be conveniently applied to object detection because the output size is fixed regardless of image size. Experiments applying the faster region-CNN to a publicly available ten-class object detection dataset demonstrate that our proposed PCP can achieve accuracy higher than that of a region of interest pooling in the HRSI object detection task.

Sea surface temperature (SST) is an important factor in the global ocean–atmosphere system, being vital in a variety of climate analyses and air–sea interaction research studies. However, estimating daily SST with both high precision and high spatial completeness remains a challenge. This article attempts to solve this problem by merging two complementary daily SST products, that is, the 25 km-resolution Advanced Microwave Scanning Radiometer for EOS (AMSR-E) SST and 4 km-resolution Moderate Resolution Imaging Spectroradiometer (MODIS) SST, using a genetic algorithm–assisted deep neural network model (GA-DNNM). The merged SST with a spatial resolution of 4 km and a temporal resolution of 1 day is achieved. Experiments in the Asia and Indo-Pacific Ocean (AIPO) region in 2005 were conducted to demonstrate the feasibility and advantages of the proposed method. Results showed that the spatial coverages of the original MODIS SST and AMSR-E SST are ranging from 25.0 to 48.1%, and 31.5 to 47.6%, respectively, while the merged SST achieves a spatial coverage ranging from 56.1 to 73.1%, with improvements ranging from 50.2 to 131.7% relative to the original MODIS SST. Comparisons with drifting buoy observations indicate that the merged SST is accurate, with an average bias of 0.006°C and an average RMSE of 0.502°C, in places where the MODIS SST data are missing before being merged in the AIPO area, and with an average bias of −0.082 °C, and an average RMSE of 0.603°C for the merged SST in the whole study area.

Deep convolutional neural networks (DCNNs) have shown significant improvements in remote sensing image scene classification for powerful feature representations. However, because of the high variance and volume limitations of the available remote sensing datasets, DCNNs are prone to overfit the data used for their training. To address this problem, this paper proposes a novel scene classification framework based on a deep Siamese convolutional network with rotation invariance regularization. Specifically, we design a data augmentation strategy for the Siamese model to learn a rotation invariance DCNN model that is achieved by directly enforcing the labels of the training samples before and after rotating to be mapped close to each other. In addition to the cross-entropy cost function for the traditional CNN models, we impose a rotation invariance regularization constraint on the objective function of our proposed model. The experimental results obtained using three publicly-available scene classification datasets show that the proposed method can generally improve the classification performance by 2~3% and achieves satisfactory classification performance compared with some state-of-the-art methods.

Crop residue burning is the major biomass burning activity in China, strongly influencing the regional air quality and climate. As the cultivation pattern in China is rather scattered and intricate, it is a challenge to derive an accurate emission inventory for crop residue burning. In this study, we proposed a remote sensing-based method to estimate nitrogen oxide (NOx) emissions related to crop residue burning at the field level over Hubei, China. The new method considers differences in emission factors and the spatial distribution for different crop types. Fire radiative power (FRP) derived from moderate-resolution imaging spectroradiometer (MODIS) was used to quantify NOx emissions related to agricultural biomass combustion. The spatial distribution of different crops classified by multisource remote sensing data was used as an a priori constraint. We derived a new NOx emission database for Hubei from 2014 to 2016 with spatial resolution of 1 × 1 km. Significant seasonal patterns were observed from the NOx emission database. Peak NOx emission occurring in October was related to the residue burning in late autumn harvesting. Another peak was observed between January and April, which was due to the frequent burning of stubble before spring sowing. Our results were validated by comparing our emission inventory with geostationary satellite observations, previous studies, global fire emission database (GFED), NO2 vertical column densities (VCDs) from ozone monitoring instrument (OMI) satellite observations, and measurements from environmental monitoring stations. The comparisons showed NOx emission from GFED database was 47% lower than ours, while the evaluations from most of the statistical studies were significantly higher than our results. The discrepancies were likely related to the differences of methodology and data sources. The spatiotemporal variations of NOx emission in this study showed strong correlations with NO2 VCDs, which agreed well with geostationary satellite observations. A reasonable correlation between in situ NO2 observations and our results in agricultural regions demonstrated that our method is reliable. We believe that the new NOx emission database for crop residue burning derived in this study can potentially improve the understanding of pollution sources and can provide additional information for the design of pollution control measures.

Accurate and fine-grained discovery by diverse Earth observation (EO) sensors ensures a comprehensive response to collaborative observation-required emergency tasks. This discovery remains a challenge in an EO sensor web environment. In this study, we propose an EO sensor observation capability metadata model that reuses and extends the existing sensor observation-related metadata standards to enable the accurate and fine-grained discovery of EO sensors. The proposed model is composed of five sub-modules, namely, ObservationBreadth, ObservationDepth, ObservationFrequency, ObservationQuality and ObservationData. The model is applied to different types of EO sensors and is formalized by the Open Geospatial Consortium Sensor Model Language 1.0. The GeosensorQuery prototype retrieves the qualified EO sensors based on the provided geo-event. An actual application to flood emergency observation in the Yangtze River Basin in China is conducted, and the results indicate that sensor inquiry can accurately achieve fine-grained discovery of qualified EO sensors and obtain enriched observation capability information. In summary, the proposed model enables an efficient encoding system that ensures minimum unification to represent the observation capabilities of EO sensors. The model functions as a foundation for the efficient discovery of EO sensors. In addition, the definition and development of this proposed EO sensor observation capability metadata model is a helpful step in extending the Sensor Model Language (SensorML) 2.0 Profile for the description of the observation capabilities of EO sensors.

In the Earth Observation sensor web environment, the rapid, accurate, and unified discovery of diverse remote sensing satellite sensors, and their association to yield an integrated solution for a comprehensive response to specific emergency tasks pose considerable challenges. In this study, we propose a remote sensing satellite sensor object model, based on the object-oriented paradigm and the Open Geospatial Consortium Sensor Model Language. The proposed model comprises a set of sensor resource objects. Each object consists of identification, state of resource attribute, and resource method. We implement the proposed attribute state description by applying it to different remote sensors. A real application, involving the observation of floods at the Yangtze River in China, is undertaken. Results indicate that the sensor inquirer can accurately discover qualified satellite sensors in an accurate and unified manner. By implementing the proposed union operation among the retrieved sensors, the inquirer can further determine how the selected sensors can collaboratively complete a specific observation requirement. Therefore, the proposed model provides a reliable foundation for sharing and integrating multiple remote sensing satellite sensors and their observations.

Observation schedules depend upon the accurate understanding of a single sensor’s observation capability and the interrelated observation capability information on multiple sensors. The general ontologies for sensors and observations are abundant. However, few observation capability ontologies for satellite sensors are available, and no study has described the dynamic associations among the observation capabilities of multiple sensors used for integrated observational planning. This limitation results in a failure to realize effective sensor selection. This paper develops a sensor observation capability association (SOCA) ontology model that is resolved around the task-sensor-observation capability (TSOC) ontology pattern. The pattern is developed considering the stimulus-sensor-observation (SSO) ontology design pattern, which focuses on facilitating sensor selection for one observation task. The core aim of the SOCA ontology model is to achieve an observation capability semantic association. A prototype system called SemOCAssociation was developed, and an experiment was conducted for flood observations in the Jinsha River basin in China. The results of this experiment verified that the SOCA ontology based association method can help sensor planners intuitively and accurately make evidence-based sensor selection decisions for a given flood observation task, which facilitates efficient and effective observational planning for flood satellite sensors.

An accurate and comprehensive representation of an observation task is a prerequisite in disaster monitoring to achieve reliable sensor observation planning. However, the extant disaster event or task information models do not fully satisfy the observation requirements for the accurate and efficient planning of remote-sensing satellite sensors. By considering the modeling requirements for a disaster observation task, we propose an observation task chain (OTChain) representation model that includes four basic OTChain segments and eight-tuple observation task metadata description structures. A prototype system, namely OTChainManager, is implemented to provide functions for modeling, managing, querying, and visualizing observation tasks. In the case of flood water monitoring, we use a flood remote-sensing satellite sensor observation task for the experiment. The results show that the proposed OTChain representation model can be used in modeling process-owned flood disaster observation tasks. By querying and visualizing the flood observation task instances in the Jinsha River Basin, the proposed model can effectively express observation task processes, represent personalized observation constraints, and plan global remote-sensing satellite sensor observations. Compared with typical observation task information models or engines, the proposed OTChain representation model satisfies the information demands of the OTChain and its processes as well as impels the development of a long time-series sensor observation scheme.

Sensor inquirers cannot understand comprehensive or accurate observation capability information because current observation capability modeling does not consider the union of multiple sensors nor the effect of geospatial environmental features on the observation capability of sensors. These limitations result in a failure to discover credible sensors or plan for their collaboration for environmental monitoring. The Geospatial Environmental Observation Capability (GEOC) is proposed in this study and can be used as an information basis for the reliable discovery and collaborative planning of multiple environmental sensors. A field-based GEOC (GEOCF) information representation model is built. Quintuple GEOCF feature components and two GEOCF operations are formulated based on the geospatial field conceptual framework. The proposed GEOCF markup language is used to formalize the proposed GEOCF. A prototype system called GEOCapabilityManager is developed, and a case study is conducted for flood observation in the lower reaches of the Jinsha River Basin. The applicability of the GEOCF is verified through the reliable discovery of flood monitoring sensors and planning for the collaboration of these sensors.

Post-industrial regeneration, the conversion and integration of brown lands into green spaces, has become a prevalent process in contemporary urban sustainable development. Previous research on post-industrial landscapes has mostly focused on qualitative studies and paid little attention to the visual and physical attributes of these landscapes, providing little quantitative analyses of their physical qualities. We examined the relationship between landscape characteristics and individual perceptions and preferences of post-industrial landscapes. We used statistical modeling, including multivariate stepwise regression models, to involve the multidimensional integration of participants’ physiological responses, eye-tracking responses, and mental activity data. We found: 1) The hypothesis that “coherence and legibility may not serve as mediating factors in the relationship between low-level image features and preference as well as positive perception“ has been rejected. 2) The post-industrial landscape has unique aesthetic features of “Original – New Placement”. In this study, participants preferred artificial to natural scenes. 3) The significant factors in enhancing participants’ perceptions and preferences were the increase in the percentages of industrial remains, new construction, and ground-covering plants elements. 4) The type of artificial views in the post-industrial landscape has been positively influenced by the sense of industrial historical atmosphere and the sense of aesthetic appeal for industrial remains. 5) The percentage of water in post-industrial waterfront environments might reduce participants’ initial attraction to industrial remains in their original location. In application, these findings could help improve public preference and satisfaction in the design of post-industrial landscapes.

Urban green spaces shaped by the post-industrial landscape possess distinctive characteristics and aesthetic features due to the exceptional properties of industrial remains. Previous studies have indicated that various types of urban green spaces without industrial remains, such as urban parks, waterfronts, and streets, have a positive impact on the public's physiological and psychological well-being. However, the extent and mechanisms of the public's response to post-industrial landscapes remain unclear. To investigate mechanisms of public perceptions of and preferences for post-industrial landscape types and elements, we conducted quantitative analysis by coupling multimodal data and comparative or difference analyses among urban green spaces. We conducted a randomized controlled experiment with 48 participants who viewed images of different combinations of post-industrial landscapes in a distraction-free environment. After a pause, Positive-Negative perception and Preference questionnaires were completed. Eye tracking data were recorded during the experiment. Changes in electrodermal activity and heart rate variability were used to measure physiological stress. This study employed Pearson's correlation model to examine the relationships between objective data and subjective data. The ANOVA test was utilized to investigate the variability of objective and subjective data across different groups. Additionally, a multiple-stepwise regression model was employed to analyze the specific influencing factors and their respective degrees of influence. We found that (1) artificial landscape elements in post-industrial landscapes were more appealing to participants and heightened their sense of stress; natural landscape elements can alleviate stress and promote restoration. (2) The percentage of flowering shrub and tree elements was significantly positively correlated with preference, while the percentage of ground-covering plant elements was significantly negatively correlated with preference. (3) Industrial construction was significantly positively correlated with the sense of historical value while industrial construction and pavement elements negatively correlated with preference. However, pavement elements significantly mitigated the sense of insecurity, poor accessibility, and pollution risk. (4) Industrial construction and pavement distinguished the post-industrial landscape from other green spaces without industrial remains while maximizing historical value and curiosity helped increase positive effects. Although impact mechanisms of natural elements in other green spaces without industrial remains showed homogeneous similarities, the scene composed of industrial mixed with natural elements may lead to different perceptions. Our findings indicate that multimodal data coupled with comparative analysis of multiple green space types can help to fully identify mechanisms by which landscape types and elements influence public perceptions and preferences. This understanding can help increase public satisfaction with post-industrial landscapes and enable researchers to determine the sustainability of post-industrial sites using interrogative design.