Change detection (CD) is one of the main applications of remote sensing. With the increasing popularity of deep learning, most recent developments of CD methods have introduced the use of deep ...learning techniques to increase the accuracy and automation level over traditional methods. However, when using supervised CD methods, a large amount of labeled data is needed to train deep convolutional networks with millions of parameters. These labeled data are difficult to acquire for CD tasks. To address this limitation, a novel semisupervised convolutional network for CD (SemiCDNet) is proposed based on a generative adversarial network (GAN). First, both the labeled data and unlabeled data are input into the segmentation network to produce initial predictions and entropy maps. Then, to exploit the potential of unlabeled data, two discriminators are adopted to enforce the feature distribution consistency of segmentation maps and entropy maps between the labeled and unlabeled data. During the competitive training, the generator is continuously regularized by utilizing the unlabeled information, thus improving its generalization capability. The effectiveness and reliability of our proposed method are verified on two high-resolution remote sensing data sets. Extensive experimental results demonstrate the superiority of the proposed method against other state-of-the-art approaches.
Rapid global economic development has resulted in a corresponding intensification of urbanization, which has in turn impacted the ecology of vast regions of the world. A series of problems have thus ...been introduced, such as changes in land-use/land-cover (LULC) and changes in local climate. The process of urbanization predominantly represents changes in land-use, and is deemed by researchers to be the chief cause of climate change and ecological change. One of the principal purposes of the research in this field is to find ways to mitigate the influence of land-use change on local or global environments. In the study presented in this article, satellite images were utilized to extract information regarding land-use in Beijing City, and to develop maps of land surface temperature (LST) during two different periods of time: 2 August 1999 and 8 August 2010. A supervised classification scheme, a support vector machine, was used to derive the land-use change map for the above periods. Maps of surface temperature are derived from the thermal band of Landsat images using the mono-window algorithm. Results from post-classification comparison indicated that an increase in impervious surface areas was found to be dramatic, while the area of farmland decreased rapidly. The changes in LULC were found to have led to a variation in surface temperature, as well as a spatial distribution pattern of the urban heat island phenomenon. This research revealed that the hotspots were mainly located in areas dominated by three kinds of material: bare soil, rooftops, and marble surfaces. Results from the local Moran's I index indicated that the use of lower surface temperature materials will help to mitigate the influence of the urban heat island phenomenon. The results of this research study provide a reference for government departments involved in the process of designing residential regions. Such a reference should enable the development of areas sympathetic to environmental changes and hence mitigate the effects of the growing intensity of urbanization.
ABSTRACTLi, F, Newton, RU, Shi, Y, Sutton, D, and Ding, H. Correlation of eccentric strength, reactive strength, and leg stiffness with running economy in well-trained distance runners. J Strength ...Cond Res XX(X)000–000, 2019—Neuromuscular characteristics play a critical role in distance running performance; however, their relationship with running economy (RE) remains unclear. The purpose of this study was to evaluate the correlations between 1 repetition maximum (1RM) strength, eccentric strength, reactive strength, leg stiffness, and RE at 12–16 km·h among well-trained male runners. Twenty-eight male collegiate distance runners participated in test sessions on 3 separate days. In the first session, their 1RM squat strength, countermovement jump (CMJ), and drop jump performances were measured. In the second session, the leg press (LP) eccentric and concentric peak force, and leg stiffness (Kleg) were evaluated. In the final session, 12, 14, and 16 km·h RE, blood lactate concentration, and maximum oxygen uptake were measured. There were significant relationships between the LP eccentric peak force, eccentric:concentric peak force ratios (Efl:Cex), RE at speeds of 12, 14, and 16 km·h (r = −0.527 to −0.630; p < 0.01), reactive strength index (r = −0.419 to −0.572; p < 0.05), and Kleg (r = −0.686 to −0.761; p < 0.001) were significantly correlated with RE at 12, 14, and 16 km·h. No significant association was found between LP concentric peak force, 1RM squat strength, CMJ, and RE at any speed (p > 0.05). Superior RE among distance runners may be related to greater eccentric strength, elastic energy utilization, and stiffer lower limbs during running but not to maximal muscle strength per se. Coaches should focus on these neuromuscular characteristics to improve running performance.
Sea surface temperature (SST) constitutes a pivotal physical parameter in the investigation of atmospheric, oceanic, and air–sea exchange processes. The retrieval of SST through satellite passive ...microwave (PMW) technology effectively mitigates the interference posed by cloud cover, addressing a longstanding challenge. Nevertheless, conventional functional representations often fall short in capturing the intricate interplay of factors influencing SST. Leveraging neural networks (NNs), known for their adeptness in tackling nonlinear and intricate problems, holds great promise in SST retrieval. Nonetheless, NNs exhibit a high sensitivity to initial weights and thresholds, rendering them susceptible to local optimization issues. In this study, we present a novel machine learning (ML) approach for SST retrieval using PMW measurements, drawing from the Sparrow Search Algorithm (SSA) and Back-Propagation neural network (BPNN) methodologies. The core premise involves the optimization of the BP neural network’s initial weights and thresholds through an enhanced SSA algorithm employing various optimization strategies. This optimization aims to provide superior parameters for the training of the BP neural network. Employing AMSR2 brightness temperature data, sea surface wind speed data, and buoy SST measurements, we construct the ISSA-BP model for sea surface temperature retrieval. The validation of the ISSA-BP model against the test data is conducted and compared against the multiple linear regression (MLR) model, an unoptimized BP model, and an unimproved SSA-BP model. The results manifest an impressive R-squared (R2) value of 0.9918 and a root-mean-square error (RMSE) of 0.8268 °C for the ISSA-BP model, attesting to its superior accuracy. Furthermore, the ISSA-BP model was applied to retrieve global sea surface temperatures on 15 July 2022, yielding an R2 of 0.9926 and an RMSE of 0.7673 °C for the OISST product on the same day, underscoring its excellent concordance. The results indicate that SST can be efficiently and accurately retrieved using the model proposed in this paper, based on satellite PMW measurements. This finding underscores the potential of employing machine learning algorithms for SST retrieval and offers a valuable reference for future studies focusing on the retrieval of other sea surface parameters.
Vegetation serves as an indicator of ecological change, and phenology is an important indicator for evaluating vegetation growth and development. Analyzing the spatiotemporal characteristics of ...vegetation phenology and its driving factors is of great significance for analyzing the carbon, water, and energy balance of terrestrial ecosystems. To better assess the impact of external environmental changes on vegetation phenology and comprehend the changing trends of phenology, this study employed phenological parameters as response variables and incorporated meteorological and urbanization factors as explanatory variables. A generalized additive model (GAM) was constructed meticulously to investigate how vegetation phenology responds to climate change and urbanization in Beijing, as well as to predict vegetation phenology. The results showed that there were nonlinear relationships between the vegetation phenological parameters, i.e., start of season (SOS) and end of season (EOS), and external environmental changes. Formula Omitted of the GAM predicted SOS and EOS with respect to the observed data increased to 0.622 and 0.756, respectively. The prediction effects in each region of the urban–rural gradient zone were better with the root-mean-square error of approximately 4–7 days. This study demonstrates that the GAM considers the nonlinear relationships between vegetation phenology and external environmental factors. The validation results based on the observed data show that the models are reliable, and the findings can provide theoretical references for urban development planning and ecological environmental protection in Beijing.
Water temperature is a key factor used to assess biogeochemical cycles and aquatic habitat quality, and is typically monitored using in situ sensors deployed on distributed piers, buoys or mobile ...platforms. Due to multiple, spatially and temporally varying influences on surface water temperature, (e.g., solar radiation, water depth, tidal stage, turbidity, and industrial activities) multi-temporal remote sensing observations might effectively be used to link these drivers with observations. However, while low- to moderate-resolution sensors provide temporally continuous observations, large pixel sizes have proven problematic in coastal regions where shoreline influences on pixel radiance contaminate the radiation signal leaving the water surface. To alleviate this problem, we used a dense stack of Landsat TM/ETM+ thermal imagery organized by day of year of acquisition, thus producing a climatology of water temperature. We use these data to analyze the spatial patterns of water surface temperature climatology (e.g., average maximum and minimum temperatures) for the past thirty years. We also explore the impact of power plant thermal effluent on water surface temperature climatology of the Chesapeake Bay tributaries. Finally, we divide the Landsat record into 5-year intervals, and calculate the water surface temperature climatology for each period. Trends in water surface temperature over the Landsat record were then compared against air temperature records available from coastal NOAA weather stations. The resulting data exhibit broad scale patterns, such as water surface climatology differences between the main stem of the Bay and its tributaries. The results also include the influence of urbanization and industrialization such as increases in impervious surface area and thermal effluent from power plants. Trends of increasing water surface temperature and air temperature were found for more than 92% of the Bay. While water temperature was always ~2-3 degree cooler than the air temperature, water temperature has been increasing more rapidly than air temperature in some areas, particularly in the main stem of the Bay and in the Potomac estuary. Therefore, there is a detectable impact of global change on the Chesapeake Bay in the form of an increase in water temperature, which can only partially be explained by increasing air temperatures.
Change detection (CD) methods work on the basis of co-registered multi-temporal images with equivalent resolutions. Due to the limitation of sensor imaging conditions and revisit period, it is ...difficult to acquire the desired images, especially in emergency situations. In addition, accurate multi-temporal images co-registration is largely limited by vast object changes and matching algorithms. To this end, a resolution- and alignment-aware change detection network (RACDNet) is proposed for multi-resolution optical remote-sensing imagery CD. In the first stage, to generate high-quality bi-temporal images, a light-weighted super-resolution network is proposed by fully considering the construction difficulty of different regions, which facilitates to detailed information recovery. Adversarial loss and perceptual loss are further adopted to improve the visual quality. In the second stage, deformable convolution units are embedded in a novel Siamese–UNet architecture for bi-temporal deep features alignment; thus, robust difference features can be generated for change information extraction. We further use an atrous convolution module to enlarge the receptive field, and an attention module to bridge the semantic gap between the encoder and decoder. To verify the effectiveness of our RACDNet, a novel multi-resolution change detection dataset (MRCDD) is created by using Google Earth. The quantitative and qualitative experimental results demonstrate that our RACDNet is capable of enhancing the details of the reconstructed images significantly, and the performance of CD surpasses other state-of-the-art methods by a large margin.
Hyperspectral image (HSIs) denoising is a preprocessing step that plays a crucial role in many applications used in Earth observation missions. Low-rank tensor representation can be utilized to ...restore mixed-noise HSIs, such as those affected by mixed Gaussian, impulse, stripe, and deadline noises. Although there is a considerable body of research on spatial and spectral prior knowledge concerning subspace, the correlation between the spectral continuity and the nonlocal sparsity of the spectral and spatial factors is not yet fully understood. To address this deficiency, in the present study, we determined the correlation between these factors using a cascaded technique, and we describe in this paper the double-factor tensor cascaded-rank (DFTCR) minimization method that was used. The information existing in the nonlocal sparsity property of the spatial factor was employed to promote a geometrical feature representation, and a tensor cascaded-rank minimization approach was introduced as a nonlocal self-similarity to promote restoration quality. The continuity between the difference and nonlocal gradient sparsity constraints of the spectral factor was also introduced to learn the basis. Furthermore, to estimate the solutions of the proposed model, we developed an algorithm based on the alternating direction method of multipliers (ADMM). The performance of the DFTCR method was tested by a comparison with eleven established denoising methods for HSIs. The results showed that the proposed DFTCR method exhibited superior performance in the removal of mixed noise from HSIs.
Net primary productivity (NPP), as an indicator of ecological functioning, plays an important role in regional and global carbon cycles. Although many studies have estimated the NPP of vegetation on ...the Qinghai Plateau (QP), the existing NPP datasets over the QP are either of low spatial resolution or limited-duration time-series. These shortcomings restrict our ability to explore the spatial distribution and long-term trends of NPP at a finer scale. To address this gap, we present a new monthly NPP dataset (QP_NPP30) at a high spatial resolution (30 m) over the QP for the period 1987-2021. We constructed this dataset using the Carnegie-Ames-Stanford-Approach (CASA) model and multisource data, including reconstructed normalized difference vegetation index (NDVI) data, reanalysis data, land cover, and other ancillary data. To reconstruct the NDVI, a harmonic regression model based on the Google Earth Engine (GEE) was applied to the NDVI time series data. Statistical analysis of QP_NPP30 showed that the NPP in the QP has increased over the past 35 years (0.92 <inline-formula><tex-math notation="LaTeX">g C/m^{2}/yr</tex-math></inline-formula>). Furthermore, we found that NPP is concentrated in June, July, and August, accounting for approximately 73% of the annual total. To validate our dataset, we compared it with measured NPP and with the MODIS NPP product (MOD-NPP). Our results demonstrated that QP_NPP30 has similar spatial patterns to MOD-NPP, but offers richer spatial detail. Specifically, QP_NPP30 has a higher accuracy than MOD-NPP, by comparing with the measured data (r = 0.695, RMSE = 132.823 <inline-formula><tex-math notation="LaTeX">g C/m^{2}/yr</tex-math></inline-formula> for QP_NPP30; r = 0.328, RMSE = 158.586 <inline-formula><tex-math notation="LaTeX">g C/m^{2}/yr</tex-math></inline-formula> for MOD-NPP).
Spectral features in remote sensing images are extensively utilized to detect land cover changes. However, detection noise appearing in the changing maps due to the abundant spatial details in the ...high-resolution images makes it difficult to acquire an accurate interpretation result. In this paper, an object-oriented change detection approach is proposed which integrates spectral–spatial–saliency change information and fuzzy integral decision fusion for high-resolution remote sensing images with the purpose of eliminating the impact of detection noise. First, to reduce the influence of feature uncertainty, spectral feature change is generated by three independent methods, and spatial change information is obtained by spatial feature set construction and the optimal feature selection strategy. Secondly, the saliency change map of bi-temporal images is obtained with the co-saliency detection method to complement the insufficiency of image features. Then, the image objects are acquired by multi-scale segmentation based on the staking images. Finally, different pixel-level image change information and the segmentation result are fused using the fuzzy integral decision theory to determine the object change probability. Three high-resolution remote sensing image datasets and three comparative experiments were carried out to evaluate the performance of the proposed algorithm. Spectral–spatial–saliency change information was found to play a major role in the change detection of high-resolution remote sensing images, and the fuzzy integral decision strategy was found to effectively obtain reliable changed objects to improve the accuracy and robustness of change detection.