Improved estimation of coalbed methane content using the revised estimate of depth and CatBoost algorithm: A case study from southern Sichuan Basin, China

Lu, Chengang; Zhang, Suian; Xue, Dan; Xiao, Fengchao; Liu, Cheng

doi:10.1016/j.cageo.2021.104973

Cited by 38 publications

(11 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Meanwhile, the parameter a > 0. Furthermore, adding the prior value and the prior weight in the CatBoost algorithm ensures the noise obtained from low-frequency categories is reduced [104]. Prokhorenkova et al [99], in their pioneer CatBoost article, compared its performance with that of XG-Boost and LightGBM, and they stated that CatBoost is less likely to overfit than XGBoost or LightGBM.…”

Section: Algorithm 3 Lightgbmmentioning

confidence: 99%

A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects

2022

View full text Add to dashboard Cite

Ensemble learning techniques have achieved state-of-the-art performance in diverse machine learning applications by combining the predictions from two or more base models. This paper presents a concise overview of ensemble learning, covering the three main ensemble methods: bagging, boosting, and stacking, their early development to the recent state-of-the-art algorithms. The study focuses on the widely used ensemble algorithms, including random forest, adaptive boosting (AdaBoost), gradient boosting, extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and categorical boosting (CatBoost). An attempt is made to concisely cover their mathematical and algorithmic representations, which is lacking in the existing literature and would be beneficial to machine learning researchers and practitioners.

show abstract

Section: Algorithm 3 Lightgbmmentioning

confidence: 99%

A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects

2022

View full text Add to dashboard Cite

show abstract

“…Depleted shale gas/oil reservoirs or CBM reservoirs are typical desirable geological sites for CO 2 sequestration, all of which are rich in nanopores. Compared with pores in the conventional scale, the geological reserve in nanopores can reach as much as three to seven times that in conventional pores, , due to the huge surface area available for adsorption in nanopores. More importantly, both shale rock and coal have complex compositions, including organic matter, as well as inorganic minerals, such as quartz, feldspar, and so forth.…”

Section: Model Establishmentmentioning

confidence: 99%

Carbon Dioxide Flow Behavior through Nanopores: Implication for CO₂ Sequestration in Unconventional Gas Reservoirs

Hong-ya²,

Gang

et al. 2022

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

CO 2 sequestration is a promising approach to achieve the net-zero emission across the world, expecting to mitigate the urgent climate change and global warming. In this article, research efforts are dedicated for investigating CO 2 sequestration in unconventional gas reservoirs, characterized with nanoscale pore size and complicated mineral compositions. Unlike the majority of previous research studies focusing on CO 2 adsorption or competition adsorption in nanoconfined space, this article puts emphasis on the CO 2 flow capacity in nanopores under different conditions, including pressure, temperature, pore size, and the wettability effect. CO 2 flow capacity plays a prominent role, affecting the efficiency of CO 2 sequestration, which currently lacks due attention and entails indepth elaboration. In this article, the nanoconfined CO 2 flow mechanism is first studied, and CO 2 physical properties varying from the gaseous state to the supercritical state are incorporated in the proposed model. Furthermore, the adsorption phase thickness and critical pressure/temperature shift induced by CO 2 adsorption are coupled. Results show that (a) CO 2 flow capacity in the 2 nm pore is greater than that in the 5−20 nm pore as a result of dominant surface diffusion in small pores; (b) CO 2 flow capacity at 323 K can reach as much as 1.4 times that at 423 K, and desirable pressure for optimal CO 2 flow capacity is approximately 9 MPa in small nanopores; and (c) the wettability effect can cause as much as 96.3% discrepancy for the CO 2 flow capacity, while the surface− CO 2 contact angle varies from 20 to 160°. This work is able to contribute to CO 2 geological sequestration from the perspective of injection efficiency.

show abstract

“…In contrast to conventional neural network models, Cat Boost can adapt to training and high-precision diagnosis under small-scale data and does not need a large number of samples as a training set. Its bene ts include overcoming gradient bias, effectively resolving the issue of prediction bias, increasing the algorithm accuracy, enhancing the model generalizability, and preventing over tting [28][29][30].…”

Section: Simple Nonlinear Regression (Snr) Is a Nonlinear Regression ...mentioning

confidence: 99%

Soybean leaf estimation based on RGB images and machine learning methods

xiang

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: RGB photographs are a powerful tool for dynamically estimating crop growth. Leaves are related to crop photosynthesis, transpiration, and nutrient uptake. Traditional blade parameter measurements were labor-intensive and time-consuming. Therefore, based on the phenotypic features extracted from RGB images, it is essential to choose the best model for soybean leaf parameter estimation. This research was carried out to speed up the breeding procedure and provide a novel technique for precisely estimating soybean leaf parameters. Results: The findings demonstrate that using an Unet neural network, the IOU, PA, and Recall values for soybean image segmentation can achieve 0.98, 0.99, and 0.98, respectively. Overall, the average testing prediction accuracy (ATPA) of the three regression models is Random forest> Cat Boost > Simple nonlinear regression. The Random forest ATPAs for leaf number (LN), leaf fresh weight (LFW), and leaf area index (LAI) reached 73.45%, 74.96%, and 85.09%, respectively, which were6.93%, 3.98%, and 8.01%, respectively, higher than those of the optimal Cat Boost model and 18.78%, 19.08%, and 10.88%, respectively, higher than those of the optimal SNR model. Conclusion: The results show that the Unet neural network can separate soybeans accurately from an RGB image. The Random forest model has a strong ability for generalization and high accuracy for the estimation of leaf parameters. Combining cutting-edge machine learning methods with digital images improves the estimation of soybean leaf characteristics.

show abstract

Improved estimation of coalbed methane content using the revised estimate of depth and CatBoost algorithm: A case study from southern Sichuan Basin, China

Cited by 38 publications

References 54 publications

A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects

A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects

Carbon Dioxide Flow Behavior through Nanopores: Implication for CO₂ Sequestration in Unconventional Gas Reservoirs

Soybean leaf estimation based on RGB images and machine learning methods

Contact Info

Product

Resources

About

Improved estimation of coalbed methane content using the revised estimate of depth and CatBoost algorithm: A case study from southern Sichuan Basin, China

Cited by 38 publications

References 54 publications

A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects

A Survey of Ensemble Learning: Concepts, Algorithms, Applications, and Prospects

Carbon Dioxide Flow Behavior through Nanopores: Implication for CO2 Sequestration in Unconventional Gas Reservoirs

Soybean leaf estimation based on RGB images and machine learning methods

Contact Info

Product

Resources

About

Carbon Dioxide Flow Behavior through Nanopores: Implication for CO₂ Sequestration in Unconventional Gas Reservoirs