Comment on essd-2021-460

The precipitation oxygen isotopic composition is a useful environmental tracer for climatic and hydrological studies. However, the observed precipitation oxygen is limited at both temporal and spatial scales. Isotope-equipped general circulation models (iGCMs) can compensate for the temporal and spatial discontinuity of observation networks, but they suffer from coarse spatial resolutions and systematic biases. The objective of this study is to build a high-resolution precipitation oxygen isoscape in China for a period of 148 years by integrating observed and iGCMs-simulated precipitation oxygen isotope composition (δ18Op) using data fusion and bias correction methods. The temporal and spatial resolutions are month and 50–60 km for the isoscape, respectively. Prior to building the oxygen isoscape, the performance of two bias correction methods (BCMs) and three data fusion methods (DFMs) is compared after post-processing of eight iGCM simulations. Results show that the outputs of the Convolutional Neural Networks (CNN) fusion method exhibit the strongest correlation with observations with correlation coefficient mostly larger than 0.8, and the smallest bias with root mean square error mostly smaller than 2 ‰. The other two DFMs also perform slightly better than the two BCMs, which show similar performance. Thus, precipitation oxygen isoscape is generated by using the CNN fusion method for the 1969–2007 period in which all iGCMs have output and by using the bias correction methods for the remaining years. Based on the precipitation oxygen isoscape, the spatiotemporal patterns of δ18Op across China are investigated. The generated isoscape shows similar spatial and temporal distribution characteristics to observations. In general, the distribution pattern of δ18Op is consistent with the temperature effect in northern China, and with the precipitation amount effect in southern China, and be more specific in the Qinghai-Tibet Plateau of China. The δ18Op time series mirrors a fluctuating upward trend of the temperature or precipitation in most regions of China. The temporal and spatial distribution characteristics of the generated isoscape are consistent with the characteristics of atmospheric circulation and climate change, indicating successful assimilation and extension of the observed precipitation oxygen isotopes in time and space. Overall, the built isoscape is reliable and useful for providing strong support for tracking atmospheric and hydrological processes. The dataset is available in Zenodo at https://doi.org/10.5281/zenodo.5703811 (Chen et al., 2021).

Comparison of sixteen methods for fusion of data from impulse-radar sensors and depth sensors applied for monitoring of elderly persons

We propose a geometric data fusion (GDF) method using a perception-net which can provide error reducing, uncertainty management, and maintaining consistency. We propose a perception-net to design a state estimator for dynamic systems and apply the proposed geometric data fusion method to obtain the optimal estimate, propagate uncertainties and utilize the system knowledge. We present comparisons between the proposed estimator and the conventional estimators. It is also shown that the additional priori information on the system can be easily utilized in the proposed estimator to improve the performance. Through illustrative examples, it is verified that the proposed estimator presents better performances than existing filters and improves performances via utilizing system knowledge.

Recently, development in intelligent transportation systems (ITS) requires the input of various kinds of data in real-time and from multiple sources, which imposes additional research and application challenges. Ongoing studies on Data Fusion (DF) have produced significant improvement in ITS and manifested an enormous impact on its growth. This paper reviews the implementation of DF methods in ITS to facilitate traffic flow analysis (TFA) and solutions that entail the prediction of various traffic variables such as driving behavior, travel time, speed, density, incident, and traffic flow. It attempts to identify and discuss real-time and multi-sensor data sources that are used for various traffic domains, including road/highway management, traffic states estimation, and traffic controller optimization. Moreover, it attempts to associate abstractions of data level fusion, feature level fusion, and decision level fusion on DF methods to better understand the role of DF in TFA and ITS. Consequently, the main objective of this paper is to review DF methods used for real-time and multi-sensor (heterogeneous) TFA studies. The review outcomes are (i) a guideline of constructing DF methods which involve preprocessing, filtering, decision, and evaluation as core steps, (ii) a description of the recent DF algorithms or methods that adopt real-time and multi-sensor sources data and the impact of these data sources on the improvement of TFA, (iii) an examination of the testing and evaluation methodologies and the popular datasets and (iv) an identification of several research gaps, some current challenges, and new research trends.

Many spatiotemporal image fusion methods in remote sensing have been developed to blend highly resolved spatial images and highly resolved temporal images to solve the problem of a trade-off between the spatial and temporal resolution from a single sensor. Yet, none of the spatiotemporal fusion methods considers how the various temporal changes between different pixels affect the performance of the fusion results; to develop an improved fusion method, these temporal changes need to be integrated into one framework. Adaptive-SFSDAF extends the existing fusion method that incorporates sub-pixel class fraction change information in Flexible Spatiotemporal DAta Fusion (SFSDAF) by modifying spectral unmixing to select spectral unmixing adaptively in order to greatly improve the efficiency of the algorithm. Accordingly, the main contributions of the proposed adaptive-SFSDAF method are twofold. One is to address the detection of outliers of temporal change in the image during the period between the origin and prediction dates, as these pixels are the most difficult to estimate and affect the performance of the spatiotemporal fusion methods. The other primary contribution is to establish an adaptive unmixing strategy according to the guided mask map, thus effectively eliminating a great number of insignificant unmixed pixels. The proposed method is compared with the state-of-the-art Flexible Spatiotemporal DAta Fusion (FSDAF), SFSDAF, FIT-FC, and Unmixing-Based Data Fusion (UBDF) methods, and the fusion accuracy is evaluated both quantitatively and visually. The experimental results show that adaptive-SFSDAF achieves outstanding performance in balancing computational efficiency and the accuracy of the fusion results.

In this paper, we would focus on submitting a new decision fusion method based on multiple sensors' behaviors applying to target detection and identification in a network of distributed sensors. Each sensor has its own reliability, error rate and output data. Hence, in a processing and decision-making center in which target data are received from different sensors and sources, correctness and speed of final decision-making depend on data fusion method. The extraction, modeling and weighing of long-time and temporary behavior functions of each data source and using precise and fast decision making/fusion method are the main purpose of this article. After the introduction, we try to consider the data fusion method in decision level, such as voting schemes, rank based method and Bayesian inference. Hence, in a distributed target detection and identification system, we explain the specific and the functional features model of each source using long-time and temporary behavior functions. So we introduce the behavior based method as a new decision fusion method based on long-time and temporary behaviors of local decision makers. Therefore, we will observe that the behavior based method results, which pointed both to the temporal and the long time behaviors of the input decision makings, are very much nearer to reality and its correctness in target identification is much higher than the other methods. Examples are given corresponding to the target detection and identification systems to compare the new method with the other methods are shown that the behavior based method has its own exclusive capability in target detection, identification and producing final decision without ambiguity.

Multisource and multimodal data fusion plays a pivotal role in large-scale artificial intelligence applications involving big data. However, the choice of fusion strategies for different scenarios is often based on experimental comparisons, which leads to increased computational costs during model training and suboptimal performance during testing. In this paper, we present a theoretical analysis of early fusion, late fusion, and gradual fusion methods. We derive equivalence conditions between early and late fusions within the framework of generalized linear models. Moreover, we analyze the failure conditions of early fusion in the presence of nonlinear feature-label relationships. Furthermore, we propose an approximate equation for evaluating the accuracy of early and late fusion methods as a function of sample size, feature quantity, and modality number. We also propose a critical sample size threshold at which the performance dominance of early fusion and late fusion models undergoes a reversal. Finally, we introduce a fusion method selection paradigm for selecting the most appropriate fusion method prior to task execution and demonstrate its effectiveness through extensive numerical experiments. Our theoretical framework is expected to solve the problems of computational and resource costs in model construction, improving the scalability and efficiency of data fusion methods.

Antibiotic resistance genes (ARGs) are regarded as a major threat to public health and ecological security globally. The Dongliao River Basin is a typical farming–pastoral ecotone in the northeast of China. It is of great practical significance to explore the pollution characteristics and sources of ARGs in the Dongliao River. In this study, the Dongliao River Basin was taken as the research object, and water samples were collected at five points in the wet season, the normal season and the dry season, and the qPCR technology was used to detect the ARGs, revealing its spatial and temporal distribution characteristics. The results show that the temporal difference in ARGs was mainly in the wet season, and the contribution rates of sulfonamides (SAs) and aminoglycosides (AMs)ARGs were the largest, with relative abundance reaching 13–27% and 7–37%. In the normal season, the contribution rate of AMs ARGs further increased to 26–37%, while the contribution rate of SAs and tetracyclines (TCs) ARGs also showed a high level, accounting for 12–20% and 11–16%. In dry season, the ARGs of AMs and TCs reached 29–43% and 16–22%. As far as the spatial distribution characteristics were concerned, the absolute abundance of ARGs reached the maximum value of 3.79 × 106 copies/mL in the sampling section of Chengzishang during the wet season. In the normal season, the absolute abundance of ARGs was the largest at the sampling section of Heqing River, which was 2.62 × 106 copies/mL; While in the dry season, the absolute abundance of ARGs reached the maximum at the sampling section of Sishuang Bridge, which was 5.30 × 106 copies/mL. Furthermore, using principal component analysis–multiple linear regression (PCA–MLR) model, sul1, sul2, aadA2–03, aadA–01 genes with high absolute abundance was selected for source analysis, so as to reveal the source of ARGs pollution in Dongliao River. The results indicated that sulfonamide resistance genes (sul1, sul2) were primarily driven by nutrient salt contamination; aminoglycoside resistance genes (aadA2–03, aadA–01) exhibit sensitivity to temperature gradients, with significant proliferation during high–temperature seasons. This study provided a scientific basis for the prevention and control strategy of ARGs pollution in the Dongliao River Basin.

Biological research has shown that some mammals use low‐power seismic pulses for underground communications and navigation. For instance, the blind mole rat bangs its head against the walls of its underground tunnel to produce seismic signals. It has been demonstrated that this animal builds a three‐dimensional map of the environment by collecting and analyzing returned responses. This behavior enables the mole rat to avoid obstacles and voids while it digs its tunnels. Being able to use low‐power signals for accurate remote sensing under low signal to noise ratio (15–25 dB) conditions has some important applications (e.g., underground installment detection). A practically used method for coping with noise is based on repeated transmission of identical pulses and averaging the peak value of autocorrelation function from multiple measurements. Our research suggests that by carefully selecting a pulse family and a fusion method of multiple measurements, one can significantly improve sensing resolution. In particular, our simulation results show that employing robust statistics fusion method and by producing sonar pings with a shifting phase, the average error rate of travel time estimates can be reduced by about 30%.

In recent years, data fusion has become a very popular method in remote sensing image enhancement. In this paper, a comparative study was conducted on data fusion methods based upon SPOT5 image. First land types of forest, paddy field, dry land, water and building was selected through field survey. Then supervised classification and non-supervised classification were used upon original image and four fusion images (HIS, PCA, high-pass filtering (HPF) and Brovery) respectively. Land change area, change rate and classification accuracy were calculated. Finally suitable SPOT5 fusion method for every land types was presented. The result showed: (1) In all four fusing methods PCA held the highest land change rate, being average 49.0% for non-supervised classification and average 18.9% for supervised classification. So visual interpretation was a better way for PCA fusion image. (2) HIS produced some distortion to the original spectrum and made flaky features into pieces. This method was suitable to extract small features in complicated urban areas because of its high spatial resolution. In the research, building change rate in HIS fusing image under supervised classification was lowest, only 3.32%. (3) For HPF land change rate was low for no matter non-supervised classification or supervised classification, being average 16.3% and 11.2% respectively. This fusion method held low distortion and more high-frequency spectrum. It was suitable to be used as the basic image data for both supervised classification and non-supervised classification. In our research image classification accuracy of urban areas in HPF fusion image was 93.1%.

In this study, a temporal shape–based fusion method using a spatially and temporally moving window is proposed to incorporate time lag of fine and coarse resolution observations, and to fully utilize target fine resolution pixel and similar coarse resolution pixels in the process. This method provides high accuracy fused images with Pearson’s r of ~0.95, root mean square error of ~0.04, and bias of ~0.01 for commonly used fine spatial resolution satellites, including Landsat 7 and 8, Sentinel 2, and Gaofen 1, over different heterogeneous regions, such as urban, mountain, forest, and savanna regions. The fused fine resolution Enhanced Vegetation Index (EVI) time series using different fine spatial resolution satellites data as input are all highly correlated with the PhenoCam monitored green chromatic coordinate, with no temporal lag. Compared with commonly used data fusion method, this method provides equivalent and slightly higher accuracy because both neighboring similar pixels and the annual temporal variation are fully considered. This temporal shape–based fusion method does not require each input fine resolution image to be cloud-free; therefore, it can be used at a large spatial scale without further preprocessing and generates continuous datasets over a long-time range with only one input preparation process. The factors that could affect the method accuracy are the cloud detection accuracy of fine resolution data and the temporal continuity of the coarse resolution data. The method may also be used to produce spatially and temporally continuous surface reflectance and other surface reflectance derived indices.

It is well known that GPS can be used for localization and navigation in outside environment. Standard DGPS can be used to get an accuracy of under one meter. The precision improves but the cost is very high. The cheep single frequency GPS receiver is used in this paper to provide the positioning information. This paper proposes a new navigation data fusion method using neural network. DR (dead reckoning) navigation system can provide precise short term navigation information. But the error can accumulate over time without limitation. A BP neural network is employed to predict next sampling time GPS output and a new Kalman filter based data fusion method is proposed to do the navigation data fusion with GPS/DR system. Simulation is conducted to validate the proposed fusion method. The result shows the potential of this fusion method for outside used mobile robot navigation.

This paper designs a fixed-wing UAV postural reference system, which uses magnetometer, accelerometer and gyroscope (MARG) to perform the attitude measurement of high precision. A quaternion is calculated using Gyroscope sensor by means of quaternion algorithm, and we can get another quaternion using Magnetometer and Accelerometer sensor in the same way. The postural data are calculated using both two quaternions by two data fusion methods, adaptive complementary filter and extended Kalman filter, respectively. We compared data precision from the two filter methods in experiments. The results show that both this two fusion methods can meet the required precision of attitude data, in which Kalman filter method is more accurate than adaptive complementary filter although the latter is simpler and more practical than the former.

Continuous high spatio-temporal resolution monitoring of evapotranspiration (ET) is critical for water resource management and the quantification of irrigation water efficiency at both global and local scales. However, available remote sensing satellites cannot generally provide ET data at both high spatial and temporal resolutions. Data fusion methods have been widely applied to estimate ET at a high spatio-temporal resolution. Nevertheless, most fusion methods applied to ET are initially used to integrate land surface reflectance, the spectral index and land surface temperature, and few studies completely consider the influencing factor of ET. To overcome this limitation, this paper presents an improved ET fusion method, namely, the spatio-temporal adaptive data fusion algorithm for evapotranspiration mapping (SADFAET), by introducing critical surface temperature (the corresponding temperature to decide soil moisture), importing the weights of surface ET-indicative similarity (the influencing factor of ET, which is estimated from remote sensing data) and modifying the spectral similarity (the differences in spectral characteristics of different spatial resolution images) for the enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM). We fused daily Moderate Resolution Imaging Spectroradiometer (MODIS) and periodic Landsat 8 ET data in the SADFAET for the experimental area downstream of the Heihe River basin from April to October 2015. The validation results, based on ground-based ET measurements, indicated that the SADFAET could successfully fuse MODIS and Landsat 8 ET data (mean percent error: −5%), with a root mean square error of 45.7 W/m2, whereas the ESTARFM performed slightly worse, with a root mean square error of 50.6 W/m2. The more physically explainable SADFAET could be a better alternative to the ESTARFM for producing ET at a high spatio-temporal resolution.

This dissertation explores the intersection of data fusion, federated learning, and Bayesian methods, with a focus on their applications in indoor localization, GNSS, and image processing. Data fusion involves integrating data and knowledge from multiple sources. It becomes essential when data is only available in a distributed fashion or when different sensors are used to infer a quantity of interest. Data fusion typically includes raw data fusion, feature fusion, and decision fusion. In this thesis, we will concentrate on feature fusion. Distributed data fusion involves merging sensor data from different sources to estimate an unknown process. Bayesian framework is often used because it can provide an optimal and explainable feature by preserving the full distribution of the unknown given the data, called posterior, over the estimated process at each agent. This allows for easy and recursive merging of sensor data with prior knowledge without the need for storage. However, there are challenges in data fusion, such as the multiple counting problem, which occurs when data is utilized numerous times without the user's knowledge. In a Bayesian setting, a priori information of the unknown quantities is available and can be present among different distributed estimators. When the local estimates are fused, the prior knowledge used to construct several local posteriors might be overused unless the fusion node accounts for this and corrects it. In this thesis, we analyze the effects of shared priors in Bayesian data fusion contexts. Our analysis helps to understand the performance behavior as a function of the number of collaborative agents and different types of priors, depending on different common fusion rules. To perform this analysis, we use two divergences that are common in Bayesian inference. The generality of the results allows us to analyze very generic distributions. These theoretical results are corroborated through experiments in a variety of estimation and classification problems, including linear and nonlinear models, and federated learning schemes in a Bayesian perspective. Federated Learning is a discipline of Distributed Data Fusion that can be used for model training on local data without exchanging the data itself. This technique is useful in scenarios like image classification, indoor positioning, and jammer signal classification, where privacy concerns make data crowdsourcing difficult. In this thesis, we explore FL in two specific applications: Jammer signal and indoor positioning. Jamming signals can disrupt the operation of GNSS receivers, making jamming mitigation and localization techniques essential. Jammer classification can help with these techniques. For indoor positioning, local data points are collected to create a local fingerprinting database. Data-driven machine learning methods are used to predict the location based on this model learned without data sharing. However, Federated Learning faces several challenges, including the non-IID (non-identically distributed) problem. This problem occurs when the data distribution varies across different clients, which can lead to a decrease in performance. In this thesis, we will discuss various FL frameworks and algorithms that can help address this problem. A FL method from Bayesian perspective are proposed to deal with the problem in indoor positioning problem. Additionally, we will delve into the concepts of personalized and clustered Federated Learning. The personalized approach tailors the learning process to individual clients, which enhances the system's performance by leveraging the unique data and characteristics of each client. We will discuss the application of this approach in indoor positioning and jammer signal classification, highlighting its potential improvements and challenges. Expanding on the personalized approach, we introduce and discuss clustered Federated Learning. This learning method groups clients with similar characteristics or data patterns. Each client is typically associated with one data distribution and participates in training a model for that distribution along with their cluster peers. We propose a Bayesian framework for clustered FL, which associates clients to clusters, along with several practical algorithms for efficient learning, considering the trade-offs between performance and computational complexity. In conclusion, this thesis provides a detailed investigation and evaluation of the integration of data fusion, federated learning, and Bayesian methods. The insights and conversations presented in this study are anticipated to enhance the progress and implementation of these technologies in various domains, particularly in indoor positioning, and GNSS.--Author's abstract