Due to the diverse geology and environmental conditions in China, karst development is characterized by great variety and regional regularities. At the same time, the engineering effect involved in the construction and development work undertaken in karst regions varies considerably. This article describes the regional characteristics of karst development in China, analysis of its karst hydrogeological conditions and the main geological engineering problems in karst area. Karst environmental conditions usually include both resource factors and hazard factors. For the exploitation of different resources in karst regions, it is very important to avoid geohazards such as karst collapses, landslides, and debris flows as well as causing karst water invasion. Otherwise, according to the local hazard conditions, treatment can be implemented for decreasing the natural hazard and reducing potential harm.

In this paper, we identify and analyze a recurring training loss pattern, which we term the Epochal Sawtooth Phenomenon (ESP), commonly observed during training with adaptive gradient-based optimizers, particularly Adam optimizer. This pattern is characterized by a sharp drop in loss at the beginning of each epoch, followed by a gradual increase, resulting in a sawtooth-shaped loss curve. Through empirical observations, we demonstrate that while this effect is most pronounced with Adam, it persists, although less severely, with other optimizers such as RMSProp. We empirically analyze the mechanisms underlying ESP, focusing on key factors such as Adam’s \(\beta \) parameters, batch size, data shuffling, and sample replacement. Our analysis shows that ESP arises from adaptive learning rate adjustments controlled by the second moment estimate. Additionally, we identify the “immediate re-exposure to samples” effect during data shuffling, which causes the model to learn or memorize more at the beginning of each epoch. We also find that smaller values of \(\beta _2\) exacerbate ESP but can act as a form of regularization. While ESP is not necessarily indicative of overfitting, higher model capacity can amplify the phenomenon. To further support our analysis, we replicate ESP through a high-dimensional quadratic minimization task. We demonstrate that ESP can emerge even in simple optimization scenarios, reinforcing the generality of this pattern. The code for reproducing our experiments is available at https://github.com/qiliuchn/training-loss-pattern.

Data corruption, including missing and noisy entries, is a common challenge in real-world machine learning. This paper examines its impact and mitigation strategies through two experimental setups: supervised NLP tasks (NLP-SL) and deep reinforcement learning for traffic signal control (Signal-RL). This study analyzes how varying corruption levels affect model performance, evaluate imputation strategies, and assess whether expanding datasets can counteract corruption effects. The results indicate that performance degradation follows a diminishing-return pattern, well modeled by an exponential function. Noisy data harm performance more than missing data, especially in sequential tasks like Signal-RL where errors may compound. Imputation helps recover missing data but can introduce noise, with its effectiveness depending on corruption severity and imputation accuracy. This study identifies clear boundaries between when imputation is beneficial versus harmful, and classifies tasks as either noise-sensitive or noise-insensitive. Larger datasets reduce corruption effects but offer diminishing gains at high corruption levels. These insights guide the design of robust systems, emphasizing smart data collection, imputation decisions, and preprocessing strategies in noisy environments.

A network-level dynamic transit passenger flow estimation model based on congested schedule-based transit equilibrium assignment is proposed using observations from stop count data. A solution algorithm is proposed for the mathematical program with schedule-based transit equilibrium constraints with proven quadratic space- and time-complexities. The error bound is proven to be linearly proportional to the number of measurements. Computational experiments are conducted first to verify the methodology with two synthetic data sets (one of which is Sioux Falls compared to a benchmark model), followed by a validation of the method using bus data from Qingpu District in Shanghai, China from 1 July 2016, with 4 bus lines, 120 segments, and 55 bus stops. The estimated average of segment flows is only 2.5% off from the average of the observed segment flows; relative errors among segments are 42.5%, which fares well compared with even less complex OD estimation methods in the literature.