Predicting the microbiologically induced concrete corrosion in sewer based on XGBoost algorithm

The Effect of Microbiologically Induced Concrete Corrosion in Sewer on the Bearing Capacity of Reinforced Concrete Pipes: Full-Scale Experimental Investigation

“…This study provides limited test data, and more experimental and finite element simulation work that aims at linking the material corrosion of sewer pipes with their structural bearing capacity should be conducted in the future. According to the correlation between corrosion losses and structural bearing capacity, the remaining bearing capacity of the in-service sewer could be predicted based on the corrosion depth detected by a pipe penetrating radar [2] or predicted by a corrosion prediction model [35][36][37]. Such results can be used for condition assessment, life prediction, and risk evaluation of sewerage, further suggesting the manager make right decisions on inspection and rehabilitation.…”

Review on Microbially Influenced Concrete Corrosion

“…Kong et al [ 57 ] found that permeability is an important parameter, which characterizes the deterioration of a concrete structure. Wang et al [ 116 ] found that the corrosion product gypsum adhered to the surface of concrete coupons when exposed to a mixed freshwater effluent. An NSOM biofilm adhered to a concrete surface can penetrate concrete through cracks and pores.…”

Boosting Algorithm to Handle Unbalanced Classification of PM2.5 Concentration Levels by Observing Meteorological Parameters in Jakarta-Indonesia Using AdaBoost, XGBoost, CatBoost, and LightGBM

“…While it can be used for both classification and regression problems, all of the formulas and examples in this story refer to the algorithm's use for classification. XGBoost enhances the basic GBM framework through system optimization and algorithm improvements, following [68]- [70]: (1) parallelized tree-building where XGBoost has a sequential tree-building approach using implementations in parallel [71], (2) tree pruning where XGBoost grows the tree to max depth and then prunes backward until the increase in loss function is below a threshold [72], [73], (3) cache awareness and out-of-core computing where XGBoost designed to reduce computation time efficiently and allocate memory resources optimally [74], [75], (4) regularization is a technique used to avoid overfitting linear models and treebased models that limit, adjust or shrink the estimated coefficients towards zero [69], (5) handling missing values, and (6) built-in cross-validation whereas XGBoost comes with this method at every iteration, eliminating the need to explicitly program this seek and to specify the exact number of boosting iterations required in a single run [76]- [78].…”