As the largest freshwater storage in the world, groundwater plays an important role in maintaining ecosystems and helping humans adapt to climate change. However, groundwater dynamics, such as groundwater recharge, cannot be measured directly and is influenced by spatially and temporally complex processes, models are therefore required to capture the dynamics and provide scientific advice for decision-making. This paper developed, estimated and compared the performance of linear regression, multi-layer perception (MLP) and Long Short-Term Memory (LSTM) models in predicting groundwater recharge. The experimental dataset consists of time series of annual recharge from the year 1970 to 2012, based on water table fluctuation estimates from 465 bores in the states of South Australia and Victoria, Australia. We identified the factors that influenced groundwater recharge and found that the correlation between rainfall and groundwater recharge was strongest. The linear regression model had the poorest fitting performance, with the root mean squared error (RMSE) being greater than 0.19 when various proportions of training data were considered. The MLP model outperformed the linear regression in the prediction capability, achieving RMSE = 0.11 when 80% of training data was considered. The LSTM model was found to have the best performance, whose root mean squared errors were less than 0.12 when various proportions of training data were applied. The relative importance of influential predictors was evaluated using the above three models.

Reconstructing three-dimensional (3D) human poses is an essential step in human body animation. The purpose of this paper is to fill the gap in virtual reality research by reconstructing postures in a high-precision human model. This paper presents a new approach for 3D human pose reconstruction based on the iterative calculation of a skeleton model and conformal geometric algebra, captured by a monocular camera. By introducing the strip information of clothes and prior data of different human limbs, the location of joint points on the human body will not be affected by the occlusion problem. We then calculate the 3D coordinates of joint points based on the proposed method of the iterative calculation of the skeleton model, which can solve the high-cost problem caused by the need for multiple cameras or a depth camera. Subsequently, we utilize high-performance conformal geometric algebra (CGA) in relation to rotation transformations in order to improve the adjustment of the postures of the human limbs. Finally, realistic 3D human poses are reconstructed—specifically, the motion of the human limbs—using a rigid transformation of CGA and a smooth connection of the limb parts based on a high-precision model. Compared with the existing methods, the proposed approach can obtain satisfactory and realistic 3D human pose estimation results using grid models.

Human motion retrieval and analysis is a useful means of activity recognition to 3D human bodies. An efficient method is proposed to estimate human motion by using symmetric joint points and limb features of various limb parts based on regression task. We primarily obtain the 3D coordinates of symmetric joint points based on the located waist and hip points. By introducing three critical feature points on torso and symmetric joint points’ matching on motion video sequences, the 3D coordinates of symmetric joint points and its asymmetric limb features will not be affected by shading and interference of limb on different postures. With the asymmetric limb features of various human parts, a dynamic regulated Fuzzy neural network (DRFNN) is proposed to estimate human motion for different asymmetric postures using learning algorithm of network parameters and weights. Finally, human sequential actions corresponding to different asymmetric postures are presented according to the best retrieval results by DRFNN based on 3D human action database. Experiments show that compared with the traditional adaptive self-organizing fuzzy neural network (SOFNN) model, the proposed algorithm has higher estimation accuracy and better presentation results compared with the existing human motion analysis algorithms.

To address the need for high-precision prediction of mine water inflow under complex geological conditions, this study proposes a hybrid deep learning framework for accurate water inrush forecasting. Using daily water inrush records and nine meteorological and hydrological variables collected from the Maoping mining area in northeastern Yunnan Province, China, in 2023, five deep learning models, namely, CNN, LSTM, Transformer, CNN-LSTM, and LSTM-Transformer, were systematically developed and comparatively evaluated. The results demonstrate that the LSTM-Transformer hybrid model achieved the best predictive performance, with an MAE of 0.196, an RMSE of 0.243, and an R² of 0.882 outperforming both the individual deep learning models and other hybrid architectures. By combining the temporal memory capability of LSTM with the global attention mechanism of Transformer, the proposed model effectively captures the nonlinear, non-stationary, and multi-scale temporal dependencies embedded in mine water inflow series, thereby substantially enhancing prediction accuracy. These findings indicate that hybrid deep learning architectures integrating local temporal memory with global attention mechanisms provide a robust and effective approach for complex engineering time-series forecasting, offering valuable support for high-precision early warning and intelligent prevention of mine water inflow hazards.

Geothermal energy, a clean and reliable renewable resource, is attracting growing global attention. Predicting geothermal productivity is essential for the sustainable management of geothermal systems in conventional pumping tests, but the water level has a highly nonlinear correlation with reservoir physical conditions, and traditional numerical simulation methods fail to capture their intrinsic relationship. This study proposes a novel hybrid deep learning model of Graph Convolutional Networks (GCN) and Transformers for geothermal pumping tests, which efficiently predicts water level under nonlinear physical constraints: GCN learns the nonlinear mapping between water level depth and physical constraints, while Transformer preserves the temporal sequence correlations of production data via self-attention mechanism. Validation with test data showed that the model achieved an R² of 0.97 and an RMSE of 0.1635 m for production wells, and an R² of 0.94 and an RMSE of 3.9057 m for reinjection wells under different geological conditions. Its R² showed improvements of 13.82%, 7.83%, and 5.95% compared with the LSTM, Transformer, and GCN–LSTM models, respectively. This study provides an accurate and efficient technical approach for geothermal productivity prediction, supporting the optimization of pumping test schemes and production capacity evaluation in preliminary geothermal resource development.

For the problem of small field of view of fiber-optic image bundles imaging, an unsupervised fiber-optic image bundles imaging images stitching algorithm based on deep learning is proposed. The algorithm consists of two stages: unsupervised coarse image alignment and image reconstruction. In the first stage, we design a new backbone network that utilizes the Focus structure instead of down-sampling operations. We incorporate the ELAN structure and add attention mechanisms, which effectively enhances the backbone ’s accuracy in predicting the homography matrix while significantly reducing the model size. In the second stage, we used a more efficient convolution module C3 instead of regular convolution, reducing the number of model parameters and improving computational efficiency. Experiments are conducted using a dataset comprising fiber-optic image bundles imaging dataset and two publicly available stitching datasets (Warped MS-COCO and UDIS-D). The experimental results demonstrate that our method achieves high evaluation metrics and performs better in stitching real scene images with parallax and poor-quality fiber-optic image bundles. The network model is improved in terms of accuracy, size, and speed, meeting the practical requirements for fiber-optic image bundles imaging images stitching.