Roads，as typical man-made objects，have attracted considerable attention in the field of remote sensing. Previous research has predominantly focused on geometrical feature extraction，with relatively insufficient attention paid to road attribute information such as material, classification, and surrounding features. However，road attribute information is crucial for road management，urban planning，and more. Considering the inherent engineering and geographical relationships among these road attributes，this study adopts a multi-task learning approach. We propose a method for extracting road attributes from visible remote sensing images based on multi-task learning，utilizing a residual network integrated with a channel attention module as the backbone. This is further enhanced with a foreground auxiliary module and a feature pyramid module to augment the focus on road targets and the capability for multi-scale processing. Ultimately，the study achieves the classification of road material，classification，and surrounding feature types (background) in visible remote sensing images. and proved the overall accuracy of the network，demonstrating that convolutional networks can effectively extract features and learn engineering and geographical relationships. In the application to the periphery of a nuclear power plants，this method addressed the complex environment and strategic importance of nuclear facilities，validating its effectiveness in practical scenarios，which is of significant importance for ensuring the safe operation of nuclear power plants and the rational planning of surrounding areas.

Traditional mining operations，constrained by technological limitations such as insufficient accuracy in ore body exploration and low automation levels in mining equipment，as well as natural constraints including complex geological structures and harsh underground conditions，have long suffered from persistent systemic issues including low precision in mining processes，declining production efficiency, and accumulating safety risks，thereby severely constrained the high-quality development of the mining industry. With the rapid advancement of information technology，smart mining technology has emerged as a crucial solution to address these issues and promote industrial transformation. Based on systematic analysis and summarization of key technologies in smart mining，this study designed and developed an integrated management platform to achieve intelligent management and efficient operation of smart mines. Particularly through the integration and application of communication technologies，Internet of Things (IoT)，big data analytics，and cloud computing，this platform significantly enhances mining safety and production efficiency. Through deep integration of 5G and IoT technologies，smart mining systems have significantly improved data transmission speed and stability while supporting massive real-time data transfer. IoT devices equipped with multiple sensors enable comprehensive monitoring of environmental parameters (temperature/humidity)，equipment status，and personnel positioning，establishing a highly interconnected intelligent system. The convergence of big data and cloud computing technologies effectively addresses complex and massive data demands in mining operations，achieving real-time data sharing and distributed processing while optimizing data storage and computational efficiency. Combined with big data analytics，smart mining systems can rapidly analyze multi-dimensional data and perform deep mining to provide accurate trend predictions. Future advancements in technology and management models are expected to enable higher-level intelligentization and automation in smart mines，providing robust support for the high-quality development of the mining industry.

With the continuous promotion of government departments in water pollution prevention and control，the water environment has seen a substantial improvement，but the water bodies near pollution sources such as industrial zones and livestock and poultry farms are still prone to be black and odorous. How to identify these black stinking water bodies with excessive ammonia and nitrogen content is an urgent problem. 30 black stinky water bodies with excessive ammonia nitrogen were collected and assayed to study the identification inversion method for Gaofen-2 remote sensing data. By combining multiple band ratio and threshold segmentation algorithms，a combination algorithms applicable to the study area was obtained to identify the stinky water body and black stinky water by the correlating band ratio and the measured ammonia nitrogen. With the combination algorithms, ammonia nitrogen content of black smelly water bodies was inversed to identify the spatial distribution so as to discover the suspected sewage point position. The results were showed as the following：1) BOCI，WCI，FUI and e4 algorithms had a high separability between black smelly water bodies and general water bodies，the mean value combination of BOCI-OSTU and BOCI had the best segmentation effect on the samples of the prediction set while BOCI played the most stable role among the threshold algorithms；2) BOCI-OSTU，BOCI-mean value and WCI-Minimum are relatively effective in identifying black stinking water bodies；3)the BOI and G-R algorithms have the highest correlation of measured ammonia nitrogen values to the decision coefficients at 0.6 and 0.58 respectively；4) The ammonia nitrogen inversion was performed on three ditches within the study area using the BOI algorithm，and the ammonia nitrogen spatial distribution maps were obtained to present the suspected discharge locations. Therefore，this technique can provide efficient black stinky water body investigation service for government departments and technical support for ecological environment improvement.

With the rapid development of sandstone-type uranium exploration in China, the workload of production logging has been increasing year by year. Simultaneously, with breakthroughs in the exploration of the “second prospecting space”，the logging depth is gradually increasing to 1 000 meters. The existing logging equipment requires 2-3 downhole operations to complete uranium geophysical logging，resulting in long logging times and risks such as borehole collapse and pipe sticking. By developing a modular multi-parameter downhole sub，we have addressed the issues of mutual constraints and interference among electrical，acoustic，and radioactive parameters in logging applications. This has led to the creation of a flexible downhole probe that can be combined according to actual application needs. We have also developed an integrated ground control platform and accompanying logging data acquisition and processing software, forming a highly integrated, noise-resistant, and fast-responding digital control system. This has culminated in the development of the new-generation NDL461 digital integrated logging tool. This logging tool has passed third-party verification and has been field-tested in the Songliao，Qaidam，Yili，and Tarim basins，demonstrating its stability，accuracy，and applicability. The developed logging tool provides technical equipment support for China’s fourth-generation uranium exploration technology system.

In order to reveal the complete geological structure of Xiangshan volcanic basin and explore the metallogenic prospect and potential in the central part of the basin, the Xiangshan Uranium Field Deep Scientific Exploration phase II project deployed a 3 000 meter deep scientific borehole, named CUSD2-1, at “Xingshuxia” in the central part of the basin. To insure the smooth conduction of the drilling, we adopted the advanced AC frequency conversion electric top drive geological core drill, large diameter wireline core drilling technology, anti-inclination and control wireline core drilling tools, high efficiency diamond bit and efficient drag reducing lubricating drilling fluid, which successfully solved the technical problems of deep drilling in complex formation, such as low drilling speed in hard rock, stable hole wall in broken formation, hole leakage, anti-inclination and control in strongly deflecting formation, and safe drilling with large diameter wireline coring, and finally drilled to the predetermined depth, creating the deepest record of S (φ150 mm) diameter wireline coring in geological core drilling in China, and revealed the deep formation structure. This deep drilling provides valuable geological data for deep uranium resource exploration in Xiangshan, which not only has special significance for the scientific research and exploration of deep uranium resources, but also has great significance for the improvement of engineering technology for deep-ultra deep geological drilling.

The development of nuclear energy is inseparable from the treatment and disposal of radioactive waste. Geopolymer is a promising radioactive waste solidification material. In this study，metakaolin was used as the substrate to prepare metakaolin polymer, which was used to solidify Cs and real radioactive waste. The properties of metakaolin geopolymer were investigated by characterization and leaching experiments. Characterization experiments show that metakaolin geopolymer with three-dimensional network structure has high compressive strength, which can meet the strength requirements of radioactive waste solidified body. At the same time, the solidification of Cs in metakaolin polymer is uniform. However， the incorporation of Cs will hinder the growth of silicon and aluminum network skeleton and reduce the gel structure of the system，resulting in the increase of porosity and the decrease of compressive strength of geopolymer cured body. The leaching experiments of Cs and real waste water in deionized water and real groundwater show that metakaolin polymer has excellent Cs retention ability，and has low leaching rate and cumulative leaching fraction，which is better than the value specified in the national standard. In general，metakaolin geopolymer performs well in physical compression resistance and Cs retention，and is a material with great application potential.

In order to accurately measure ²³²Th in the waste residues of associated radioactive mines, especially for the measurement of slag samples under non-equilibrium conditions, and to provide data support for radiation environment supervision, a method for measuring ²³²Th in slag using a high-purity germanium γ spectrometer was established. The method involves indirect measurement by selecting the characteristic γ rays of the daughter nuclides in the decay chain of ²³²Th, and calculating its specific activity by the relative comparison method. The slag samples in a non-equilibrium state are sealed for 20 days to enable ²²⁸Ra and ²²⁸Ac to reach equilibrium, and ²²⁸Th, ²²⁴Ra and subsequent daughter nuclides to reach equilibrium. Then, the specific activity of the parent nuclide ²³²Th is obtained through conversion relationships. This method is accurate and efficient, with a detection limit of 1.1 Bq・kg^-1, a precision better than 5 %, and a relative error lower than 5 %. The method of measuring ²³²Th in slag using a high-purity germanium γ spectrometer does not require complex chemical treatment, which makes up for the deficiencies of inductively coupled plasma mass spectrometry. The calculation method under non-equilibrium conditions is also more reliable than using the average value of a single characteristic peak or multiple characteristic peaks.

With the rapid development of China’s nuclear power industry，the impact of thermal discharge on the surrounding marine environment is increasingly attracting attention. Objective and accurate background temperatures are crucial for accurately assessing the thermal effects of warm water discharge. In this article, the sea area near a nuclear power plant in Fujian was studied. Based on long-term thermal infrared satellite data before the operation of the first unit，the distribution of sea surface temperature field under different seasons and tidal conditions was obtained through temperature inversion. By using grid method and correlation analysis method，the sub zones with the highest temperature correlation inside and outside the submersible discharge area were determined，and a continuous background temperature field with multi-point temperature coupling was constructed. The temperature rise field was extracted using recent thermal infrared satellite data，and the impact of the operation of four units on the temperature rise in the nearby sea area was evaluated. The results shows that using the multi-point temperature substitution method to extract the reference temperature is effective and reliable. Before the operation of nuclear power，the temperature field in the study area showed significant temperature differences and band like distribution characteristics：in winter，the temperature gradually decreased from offshore to nearshore，while in summer and other months with higher temperatures，the opposite trend was observed. After the operation of the nuclear power plant，there was a significant temperature rise area in the sea area near the discharge outlet. During the ebb tide period，the temperature discharge mainly affected Qingchuan Bay，while during the flood tide period，both Qingchuan Bay and Wendu Bay were affected. The area of temperature rise exceeding 2.0 ℃ is larger in winter than in summer under the same tidal state，and the area during high tide is larger than that during low tide in the same season.

Underground Research Laboratories (URLs) play a crucial role in the siting process of high-level radioactive waste disposal. A study of evaluating the structural stability of Beishan URLs site was carried out, considering regional seismic and geological environment. After over a decade of site stability evaluations，techniques were developed to identify weakly active faults in stable crustal areas and assess their seismic potential. A method for determining design seismic motions was proposed，accounting for the source，propagation path，and local site characteristics. An efficient，high-precision time-domain analysis method for deeply buried，complex URL systems was proposed，along with a rock-structure numerical model to reveal seismic performance and its impact on the structural stability of the Beishan URL. The research determined the seismic fortification intensity for the Beishan URL，provided key seismic input parameters for structural design，and presented the seismic response results, supporting the construction of a site descriptive model (SDM) and site suitability assessment for the disposal repository.

Pingxi pluton is located in the northern section of the Taoshan-Zhuguang uranium mineralization belt，and a number of uranium mineralization occurrences have been found in the pluton by previous researchers，However，the systematical study were conducted on the uranium metallogenic conditions such as lithology，structure and alteration in the area，and the overall evaluation of uranium resource potential was not completed and no specific suggestions or opinions been put forward in the main mineralization control factors for the uranium exploration. In order to find the direction of next exploration，this paper systematically discussed the uranium mineralization characteristics of the pluton by geological investigation，physical survey and chemical analysis，analyzes the conditions of uranium mineralization and ore-controlling factors. The study concluded that the Pingxi pluton is a multi-stage S-type uranium-producing granite，with strong magmatic-tectonic hydrothermal activity，uranium mineralization is mainly controlled by the NNE-NE oriented fracture，and located at the intersection of different striking of fractures，the ore body is set in the fissures of the secondary fracture，which is often accompanied by multi-phase hydrothermal alteration，the hematitization and silicification is the main prospecting sign. The predicted favorite mineralization sectors are Shuangkeng-Fuzhu section where strong magmatic hydrothermal activity occurred in the early to late Yanshan period，with northeast trending Shankeng-Pingxi and northwest trending Luyuan-Hexi-Fuzhu ore controlling faults which extend stably into the deep with strong hydrothermal alteration such as silicification，hematitiztion and pyritization，and geophysical and geochemical anomalies are developed in the shallow and deep. Therefore there is great metallogenic potential in the deep and peripheral areas.