With the rapid development of 6G technology and the evolution of healthcare Internet of Things (IoT), federated learning has gained significant attention for privacy-preserving distributed model training in medical scenarios. However, existing approaches face challenges in addressing device heterogeneity, communication overhead, and data privacy in healthcare IoT environments. This paper proposes a resource-efficient hierarchical collaborative federated learning framework designed for next-generation 6G-enabled healthcare IoT. We introduce an adaptive edge aggregation frequency adjustment mechanism and a contribution-based dynamic model aggregation weight adjustment mechanism to enhance system training efficiency and model performance. Additionally, a resource-balanced client selection algorithm and a self-organizing federated collaborative training approach are adopted to mitigate the impact of device heterogeneity and improve resource utilization. Experimental results on two medical datasets demonstrate that our approach achieves accuracy improvements of 7.96% and 8.69% over standard federated averaging, reaching 91.58% and 87.05% accuracy respectively. The framework reduces communication overhead by up to 48.4% while maintaining effective communication ratios of 78.6% in stable network environments.

Hydrological processes drive the transport of phosphorus (P) from soil to surface water. This study is the first to use space-based observations to examine P storage in watershed lakes. Based on the vertical distribution characteristics of the total P (TP) concentration in multiple eutrophic lakes, a remote sensing estimation method for water column integrated P storage in eutrophic lakes was proposed using machine learning. The results showed that the TP profile followed a quadratic distribution that was primarily influenced by chlorophyll-a in shallow water and suspended particulate matter (SPM) in deep water. Based on this observation, a water column TP mass estimation algorithm was developed using extreme gradient boosting (XGBoost) to estimate surface TP, combined with an adjusted floating algae index (FAI) and near-infrared band. The algorithm achieved$R^{\mathbf {2}}\ge 0.6$, with the error increasing with depth. Then, water depth and lake spatial information were added to the algorithm, the average P storage of 35 large lakes in the Jianghuai region was calculated as 5347 t, and the lake area explains 85% of the P storage. The modeled P storage in Lake Taihu and Chaohu exhibited increasing trends that were mainly driven by the water level. This study is the first to observe lake P storage from space and to help elicidate the P cycle in shallow eutrophic lakes. At present, the Yangtze River Basin exports large amounts of P, lakes reduce P loss in the basin and enrich, and there is still great potential for the recycling and utilization of P resources.

The Qinghai-Tibet Plateau (QTP) is located at the roof of the world. Since its unique geography, the spatial-temporal characteristics of sporadic E layer (Es) over and around there could be hints of the coupling between upper and lower atmosphere. It also plays an important role on radio propagation at HF and VHF band. In this letter, the intensity and spatial distribution of Es over the QTP, and the response to solar activity are studied. With the bonus of the Chinese ionosonde network for more than 60 years, some conclusions are arrived at firstly for the QTP. (1) The diurnal and seasonal variations of Es layer are significant. The intensity and critical frequency are the highest at 11:00 and 12:00 LT in summer, while the lowest at sunrise in winter. (2) It is found that the Es intensity is negatively correlated with the solar cycle. In 2020, the solar minimum of 200 years, Es intensity is obvious higher than other years. (3) The Es intensity positively correlates with the terrain. Es intensity in the southeast is higher than northwest of the Plateau significantly.

Moderate-high resolution satellite missions provide an opportunity to capture subtle spatial variability in lakes; however, the sparsity of time series for individual satellite instruments cannot monitor temporal variation in the lake environment. To date, studies on the joint observations of chlorophyll-a (Chl-a) in inland lakes from multiple missions have been poorly reported. Here, we generated a harmonized Chl-a dataset for the lakes in the Yunnan–Guizhou Plateau in China from 2013 to 2022 by the Landsat 8/9 and Sentinel-2A/B virtual constellation. This study first examined the performance of four atmospheric correction processors to derive remote sensing reflectance (Rrs) from Landsat 8/9 Operational Land Imager (OLI) and Sentinel-2A/B multispectral instrument (MSI) images. We determined that the dark spectral fitting algorithm generated better Rrsthan the other processors, e.g., Rrs(561) mean absolute percentage error (MAPE)=15.2%, Rrs(665) MAPE=27.5%, and Rrs(704) MAPE=25.7%. OLI-derived Rrsat five visible and near-infrared bands showed satisfactory agreement with MSI (slope=0.94, MAPE=11.8%). The mixed density network outperformed the six state-of-the-art algorithms and other two machine learning models in retrieving Chl-a [MSI: MAPE=31.4% (N=109), OLI: MAPE=38.0% (N=74)]. The satisfactory agreement of Chl-a retrievals between the synchronous MSI and OLI images (N=2,293,821, MAPE=34.6%) supported the establishment of the virtual constellation. MSI- and OLI- derived Chl-a in nine major lakes in the studied area exhibited apparent seasonal variability from 2013 to 2022, particularly after 2017. Results highlight a solution to establish the Landsat/Sentinel-2 virtual constellation for improving the spatial and temporal resolutions of a database of lake water quality.

The Visible Infrared Imaging Radiometer Suite (VIIRS) instrument was launched to continue the legacy of the MODerate Resolution Imaging Spectroradiometer (MODIS). Despite recent studies demonstrating the use of VIIRS observations over inland waters, VIIRS has not been widely used to generate water quality products (e.g., chlorophyll-a (Chl-a), suspended particulate matter (SPM)) in relatively large turbid lakes. This study examines the quality of VIIRS-derived remote sensing reflectance (Rrs) from four different atmospheric-correction processors with matchups from 13 lakes sized between 107 km2and 2573 km2across the eastern plain of China. NOAA’s operational Rrsoutperforming Rrsretrieved by other state-of-the-art algorithms were shown to contain mean uncertainties of 57%, 33%, 20%, 28% for Rrs(486), Rrs(551), Rrs(671), and Rrs(745), respectively, which induced ~55% uncertainty in satellite-retrieved SPM and Chl-afrom recently developed algorithms in the studied lakes. A deep neural network was developed for simultaneous retrievals of Chl-aand SPM from VIIRS Rayleigh-corrected reflectance to improve accuracy. The model with satisfactory accuracy (mean uncertainty of 28% for Chl-aand 20% for SPM) outperformed other machine learning approaches and nearly halved uncertainties compared to those obtained from satellite-derived Rrsproducts. Within the 2012-2020 period, high-quality VIIRS-derived Chl-aand SPM across 61 lakes in eastern China had evident interannual variability in SPM but insignificant temporal variations in Chl-a. This study provides validated, high-quality, basin-scale VIIRS-derived Chl-aand SPM products in eastern China during the past decade. Our results offer a strategy for improving regional water quality products from VIIRS data.

Coarse-resolution sensors have been used operationally to monitor floating algal blooms with near daily revisit in coastal and inland waters. Most of the current methods in estimating fractional floating algae cover (FAC) were based on the linear pixel un-mixing assumption. In this study, a new FAC model following logistic curve was developed and applied to multisensor satellite data in two large shallow eutrophic lakes, Lake Taihu and Lake Chaohu, in China. The results indicated that after resampling to 250 m, match-up pairs of MODIS (Moderate Resolution Imaging Spectroradiometer), VIIRS (The Visible and Infrared Imager/Radiometer Suite), GOCI (Geostationary Ocean Color Imager) and OLCI (Ocean and Land Color Instrument) possessed consistent Rayleigh corrected reflectance (Rrc) and FAI (floating algae index) or AFAI (alternative floating algae index). The FAC model was developed based on the simulated AFAI data of GOCI using point spread function (PSF) and bloom percent derived from OLI (Operational Land Imager), and then was applied to MODIS, VIIRS, and OLCI. Compared with the linear pixel un-mixing method, the FAC model reflects the asymptotic reflectance saturation in the NIR (near infrared) band with the accumulation of blooms. Besides, the equivalent bloom area (EBA) of GOCI was validated using OLI matched pairs with UPD 37.6% (N=39, R2=0.96). The spatial-temporal dataset of FAC (2002-2020) shows that Lake Taihu and Lake Chaohu experienced severe algal blooms after 2010, partly resulting from the higher frequency of multisensor data. This study provides a method in building a lasting and comparable FAC dataset using multisensors.

When the circulatory roadway of a roundabout has more than two lanes, the vehicles' weaving and merging cause large traffic and safety problems. In this paper, a new method of traffic-signal control for modern roundabouts is proposed to solve problems by eliminating the conflict points and weaving sections at a roundabout with different traffic-flow rates on each approach, which normally appear in the real world. A second stop line is set exclusively for the left-turn traffic on the circulatory roadway. It is beside the first stop line on the approach. Traffic signals are installed before each stop line to eliminate the conflicts between the traffic flows on the approaches and the left-turn traffic flows on the circulatory roadway. Left-turn vehicles on the circulatory roadway will stop before red signals to avoid weaving. Equations are derived to compute the signal cycle length and the green time for each traffic flow, considering the limited queue on the circulatory roadway. Capacity and delay are also formulated to evaluate the roundabout's performance. This traffic-signal control has a successful application of a roundabout in Xiamen, China, to solve the very serious traffic-congestion problem. The signal-timing scheme was computed with the proposed equations, as well as the capacity and delay. Pictures taken before and after the improvement show the operation. After the improvement, the roundabout capacity increases 72.1% and the average delay of each vehicle decreases by 20 s.