A Query-Based Network for Rural Homestead Extraction from VHR Remote Sensing Images.

It is very significant for rural planning to accurately count the number and area of rural homesteads by means of automation. The development of deep learning makes it possible to achieve this goal. At present, many effective works have been conducted to extract building objects from VHR images using semantic segmentation technology, but they do not extract instance objects and do not work for densely distributed and overlapping rural homesteads. Most of the existing mainstream instance segmentation frameworks are based on the top-down structure. The model is complex and requires a large number of manually set thresholds. In order to solve the above difficult problems, we designed a simple query-based instance segmentation framework, QueryFormer, which includes an encoder and a decoder. A multi-scale deformable attention mechanism is incorporated into the encoder, resulting in significant computational savings, while also achieving effective results. In the decoder, we designed multiple groups, and used a Many-to-One label assignment method to make the image feature region be queried faster. Experiments show that our method achieves better performance (52.8AP) than the other most advanced models (+0.8AP) in the task of extracting rural homesteads in dense regions. This study shows that query-based instance segmentation framework has strong application potential in remote sensing images.

Weak electro-stimulation promotes microbial uranium removal: Efficacy and mechanisms.

Removal and recovery of uranium from uranium-mine wastewater is beneficial to environmental protection and resource preservation. Reduction of soluble hexavalent U (U(VI)) to insoluble tetravalent uranium (U(IV)) by microbes is a plausible approach for this purpose, but its practical implementation has long been restricted by its intrinsic drawbacks. The electro-stimulated microbial process offers promise in overcoming these drawbacks. However, its applicability in real wastewater has not been evaluated yet, and its U(VI) removal mechanisms remain poorly understood. Herein, we report that introducing a weak electro-stimulation considerably boosted microbial U(VI) removal activities in both synthetic and real wastewater. The U(VI) removal has proceeded via U(VI)-to-U(IV) reduction in the biocathode, and the electrochemical characterization demonstrates the crucial role of the electroactive biofilm. Microbial community analysis shows that the broad biodiversity of the cathode biofilm is capable of U(VI) reduction, and the molecular ecological network indicates that synthetic metabolisms among electroactive and metal-reducing bacteria play major roles in electro-microbial-mediated uranium removal. Metagenomic sequencing elucidates that the electro-stimulated U(VI) bioreduction may proceed via e-pili, extracellular electron shuttles, periplasmic and outer membrane cytochrome, and thioredoxin pathways. These findings reveal the potential and mechanism of the electro-stimulated U(VI) bioreduction system for the treatment of U-bearing wastewater.

Electrochemical removal and recovery of uranium: Effects of operation conditions, mechanisms, and implications.

Removing and recovering uranium (U) from U-mining wastewater would be appealing, which simultaneously reduces the adverse environmental impact of U mining activities and mitigates the depletion of conventional U resources. In this study, we demonstrate the application of a constant-voltage electrochemical (CVE) method for the removal and recovery of U from U-mining wastewater, in an ambient atmosphere. The effects of operation conditions were elucidated in synthetic U-bearing water experiments, and the cell voltage and the ionic strength were found to play important roles in both the U extraction kinetics and the operation cost. The mechanistic studies show that, in synthetic U-bearing water, the CVE U extraction proceeds exclusively via a single-step one-electron reduction mechanism, where pentavalent U is the end product. In real U-mining wastewater, the interference of water matrices led to the disproportionation of the pentavalent U, resulting in the formation of tetravalent and hexavalent U in the extraction products. The U extraction efficacy of the CVE method was evaluated in real U-mining wastewater, and results show that the CVE U extraction method can be efficient with operation costs ranging from $0.55/kgU ~ $64.65/kgU, with varying cell voltages from 1.0 V to 4.0 V, implying its feasibility from the economic perspective.

Developing a machine vision system for simultaneous prediction of freshness indicators based on tilapia (Oreochromis niloticus) pupil and gill color during storage at 4°C.

The study assessed the feasibility of developing a machine vision system based on pupil and gill color changes in tilapia for simultaneous prediction of total volatile basic nitrogen (TVB-N), thiobarbituric acid (TBA) and total viable counts (TVC) during storage at 4°C. The pupils and gills were chosen and color space conversion among RGB, HSI and L∗a∗b∗ color spaces was performed automatically by an image processing algorithm. Multiple regression models were established by correlating pupil and gill color parameters with TVB-N, TVC and TBA (R2=0.989-0.999). However, assessment of freshness based on gill color is destructive and time-consuming because gill cover must be removed before images are captured. Finally, visualization maps of spoilage based on pupil color were achieved using image algorithms. The results show that assessment of tilapia pupil color parameters using machine vision can be used as a low-cost, on-line method for predicting freshness during 4°C storage.