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.

How the heterogeneous and distributed atmospheric satellite sensors can achieve precise discovery and collaborative observation is a big challenge. In this study, we propose an atmospheric satellite sensor observation system meta-model that reuses and extends the existing geospatial or sensor-related metadata standards to enable the sharing and interoperability of atmospheric satellite sensors. The Open Geospatial Consortium Sensor Model Language (SensorML) has a clear hierarchy in describing the metadata framework, and it is adopted as the carrier to formalize our proposed meta-model into the Atmospheric Satellite Sensor Observation Information Model (A-SSOIM). Three different types of atmospheric satellite sensors are used to test the versatility of the proposed meta-model and the applicability of this formal expression of A-SSOIM. Results show that the proposed meta-model can be reused in all kinds of atmospheric satellite sensors to enable the sharing of atmospheric satellite sensor information and potentially promoting the interoperability of these satellite sensors.

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 (NO_x) 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 NO_x 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 NO_x emission database for Hubei from 2014 to 2016 with spatial resolution of 1 × 1 km. Significant seasonal patterns were observed from the NO_x emission database. Peak NO_x 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 NO_x 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 NO_x 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 NO_x 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.

Dynamic changes in traffic conditions cause spatiotemporal variation in traffic monitoring demand. It is, therefore, necessary to conduct efficient road monitoring to identify dynamic abnormal situations, especially in peak traffic periods. Recently, unmanned aerial vehicles (UAVs) have become an attractive solution to this problem. However, UAV monitoring routes suffer from time limitations during peak traffic hours. To optimize UAV monitoring routes during rush hours, we develop a route planning method incorporating spatiotemporal variations in monitoring demand, in which we introduce a team orienteering arc routing problem with time-varying profits (TOARP-TP) and construct a corresponding mathematical model. The TOARP-TP is an extension of an already existing routing problem, team orienteering arc routing problem (TOARP). An iterated local search (ILS)-based algorithm is designed to solve the large instances of this problem. To verify the proposed method, we conduct sets of numerical experiments with the Sioux Falls road network in South Dakota, US, and a case study is applied using Wuhan, Hubei, PRC. The results demonstrate the efficiency and practicality of our method in optimizing UAV traffic monitoring routes during rush hours. Furthermore, we discuss a strategy for scenario determination and method selection in UAV route planning.

Using digital twin models of tunnels has become critical to their efficient maintenance and management. A high-precision 3D tunnel model is the prerequisite for a successful digital twin model of tunnel applications. However, constructing high-precision 3D tunnel models with high-quality textures and structural integrity based on mobile laser scanning data remains a challenge, particularly for tunnels of different shapes. This study addresses this problem by developing a novel method for the 3D reconstruction of multi-shaped tunnels based on mobile laser scanning data. This method does not require any predefined mathematical models or projection parameters to convert point clouds into 2D intensity images that conform to the geometric features of tunnel linings. This method also improves the accuracy of 3D tunnel mesh models by applying an adaptive threshold approach that reduces the number of pseudo-surfaces generated during the Poisson surface reconstruction of tunnels. This method was experimentally verified by conducting 3D reconstruction tasks involving tunnel point clouds of four different shapes. The superiority of this method was further confirmed through qualitative and quantitative comparisons with related approaches. By automatically and efficiently constructing a high-precision 3D tunnel model, the proposed method offers an important model foundation for digital twin engineering and a valuable reference for future tunnel model construction projects.

Sensor planners find it difficult to choose the right sensor combination for observation tasks because current sensor discovery methods can only generate lists of individual sensors without considering the association between sensors that is conveyed by understanding their observation capability information. This limitation results in the failure to properly plan sensor observations and to obtain accurate observation information. The observation capability information association model (OCIAM) is proposed. An inherent state model, dynamic observation model, and correlation model are formulated in the framework of the OCIAM. The core of OCIAM is the correlation model in which four correlation modes (competitive, complementary, enhanced, and cooperative) are illustrated. A prototype system called MultisensorAssociation is developed for constructing an experiment for flood observation in the lower reaches of the Jinsha River Basin. The results of this case study verify that the OCIAM can be used for the selection of sensors or sensor combinations and has important theoretical and practical significance for multisensor observation integration management.