Monitoring the spatiotemporal variability of nutrient concentrations in shelf seas is important for understanding marine primary productivity and ecological problems. However, long time-series and high spatial-resolution nutrient concentration data are difficult to obtain using only on ship-based measurements. In this study, we developed a machine-learning approach to reconstruct monthly sea-surface dissolved inorganic nitrogen (DIN), dissolved inorganic phosphorus (DIP), and dissolved silicate (DSi) concentrations in the Yellow and Bohai seas from 2003–2019. A large amount of in situ measured data were first used to train the machine-learning model and derive a reliable model with input of environmental data (including sea-surface temperature, salinity, chlorophyll-a, and K_d490) and output of DIN, DIP, and DSi concentrations. Then, longitudinal (2003–2019) monthly satellite remote-sensing environmental data were input into the model to reconstruct the surface nutrient concentrations. The results showed that the nutrient concentrations in nearshore (water depth < 40 m) and offshore (water depth > 40 m) waters had opposite seasonal variabilities; the highest (lowest) in summer in nearshore (offshore) waters and the lowest (highest) in winter in nearshore (offshore) waters. However, the DIN:DIP and DIN:DSi in most regions were consistently higher in spring and summer than in autumn and winter, and generally exceeded the Redfield ratio. From 2003–2019, DIN showed an increasing trend in nearshore waters (average 0.14 μmol/L/y), while DSi showed a slight increasing trend in the Changjiang River Estuary (0.06 μmol/L/y) but a decreasing trend in the Yellow River Estuary (–0.03 μmol/L/y), and DIP exhibited no significant trend. Furthermore, surface nutrient concentrations were sensitive to changes in sea-surface temperature and salinity, with distinct responses between nearshore and offshore waters. We believe that our novel machine learning method can be applied to other shelf seas based on sufficient observational data to reconstruct a long time-series and high spatial resolution sea-surface nutrient concentrations.

In underwater acoustic communication (UAC) systems, the channel characteristics are mainly affected by spatiotemporal changes, which are specifically manifested by two factors: the effects of refraction and scattering caused by seawater layered media on the sound field and the random fluctuations from the sea floor and surface. Due to the time-varying and space-varying characteristics of a channel, the communication signals have significant variations in time and space. Furthermore, the signal shows frequency-selective fading in the frequency domain and signal waveform distortion in the time domain, which seriously affect the performance of a UAC system. Techniques such as error correction coding or space diversity are usually adopted by UAC systems to neutralize or eliminate the effects of deep fading and signal distortion, which results in a significant waste of limited communication resources. From the perspective of the sound field, this study used experimental data to analyze the spatiotemporal fluctuation characteristics of the signal and noise fields and then summarized the temporal and spatial variation rules. The influence of the system then guided the parameter configuration and network protocol optimization of the underwater acoustic communication system by reasonably selecting the communication signal parameters, such as frequency, bandwidth, equipment deployment depth, and horizontal distance.

The full waveform data from airborne LiDAR (Light Detection and Ranging) provides information on the distance of the target. Accurately extracting the ranging information from the full waveform data is crucial for generating point clouds. This paper introduces a method for Gaussian decomposition of full waveform data using a convolutional neural network. The method employs an improved densely connected convolutional neural network and the EM (Expectation Maximization) algorithm to extract information from the data. The method involves two key steps. First, The FWDN network preprocesses the full waveform data to enhance signal quality by reducing noise, and then the improved EM algorithm extracts Gaussian parameters (amplitude, expectation, and full width at half maximum) to obtain ranging information. Based on simulation and measured data, the decomposition success rate of this method is more than 98% with an average range accuracy of less than 1.5 cm compared to other methods. The method has significant potential for application in the field of mapping, 3D modeling.

This paper proposes a novel method to improve the clock bias short-term prediction accuracy of navigation receivers then solve the problem of low positioning accuracy when the satellite signal quality deteriorates. Considering that the clock bias of a navigation receiver is equivalent to a virtual satellite, the predicted value of clock bias is used to assist navigation receivers in positioning. Consequently, a combined prediction method for navigation receiver clock bias based on Empirical Mode Decomposition (EMD) and Back Propagation Neural Network (BPNN) analysis theory is demonstrated. In view of systematic errors and random errors in the clock bias data from navigation receivers, the EMD method is used to decompose the clock bias data; then, the BPNN prediction method is used to establish a high-precision clock bias prediction model; finally, based on the clock bias prediction value, the three-dimensional positioning of the navigation receiver is realized by expanding the observation equation. The experimental results show that the proposed model is suitable for clock bias time series prediction and providing three-dimensional positioning information meets the requirements of navigation application in the harsh environment of only three satellites.

With the aim of solving the problem of identifying complex underwater acoustic targets using a single signal feature in the Time–Frequency (TF) feature, this paper designs a method that recognizes the underwater targets based on the Delay-Doppler joint feature. First, this method uses symplectic finite Fourier transform (SFFT) to extract the Delay-Doppler features of underwater acoustic signals, analyzes the Time–Frequency features at the same time, and combines the Delay-Doppler (DD) feature and Time–Frequency feature to form a joint feature (TF-DD). This paper uses three types of convolutional neural networks to verify that TF-DD can effectively improve the accuracy of target recognition. Secondly, this paper designs an object recognition model (TF-DD-CNN) based on joint features as input, which simplifies the neural network’s overall structure and improves the model’s training efficiency. This research employs ship-radiated noise to validate the efficacy of TF-DD-CNN for target identification. The results demonstrate that the combined characteristic and the TF-DD-CNN model introduced in this study can proficiently detect ships, and the model notably enhances the precision of detection.

During the flight of a UAV (unmanned aerial vehicle), the LiDAR device undergoes random vibrations due to the changing flight attitude and wind speed conditions of the UAV. It is important to control the frequency and amplitude of the vibrations within a reasonable range by means of a damping structure. As the vibrations caused by various factors during flight are random and non-linear, this paper innovates the analysis principle and damping control means for the random vibrations of airborne optoelectronic devices. The response spectrum analysis theory is used to establish the shock response spectrum, and an optimised and improved recursive digital filtering method is used to fit the frequencies of random vibration to the synthetic shock response. Considering the uncertainty of the vibration excitation signal, a virtual excitation method is used for the first time to simulate the random vibration to which the radar may be subjected in the air, and to simplify the calculation steps. The shock plate structure is designed using a multi-point control method to innovate a passive response to the random excitation. Finally, a modal analysis of the synthesised impact response was carried out. It is verified that the first six modal frequencies are controlled within 220 Hz, realising the frequency reduction. The amplitude of the three x, y, and z directions is controlled to within 0.5 mm, thus achieving vibration damping.