Search

In the implementation process of carbon capture and storage (CCS), the geomechanical problems arising from the cyclic injection of carbon dioxide into the formation cannot be ignored. To clarify the influence of cyclic loading on the geomechanics properties of reservoir rocks, cyclic loading tests were carried out on rocks in sandstone reservoirs with the RTR-2000 Rock Mechanics Test System, and the evolution of compressive strength, elastic modulus, and Poisson’s ratio parameters was analyzed, which revealed the law of the geomechanical deterioration and damage evolution of sandstone reservoirs under cyclic loading. The results show that under the same cyclic load, when the number of cycles is increased to a certain degree, the influence on the peak strength is small. As the number of cycles increases, the modulus of elasticity of rock appears to be increasing and then decreasing, whereas a rapid increase in Poisson’s ratio and a slow increase in Poisson’s ratio occur with the increase in the number of cycles. Under the same number of cycles, the peak strength of the core gradually decreased with the increase of the maximum cyclic stress. When the cyclic load was smaller than the yield stress of the core, the effect of cyclic loading on the strength of the core was small, and when the cyclic load was larger than the yield stress, the effect of cyclic loading on the strength increased significantly. With the increase of cyclic load, the modulus of elasticity showed a tendency to increase and then decrease, and Poisson’s ratio had a tendency of decreasing and the overall degree of change was small.

Data transformation of the reference soil organic matter (SOM) decomposition rates (kref), often derived as turnover times or in alternative formats, is commonly used to develop ecological models for projecting the persistence of SOM. However, the effects of reciprocal or logarithmic transformation of kref on model performance and edaphic‐climatic patterns remain uncertain. Here, we convert published kref values into reciprocal or logarithmic formats and establish machine learning models between the transformed kref and edaphic‐climatic predictors. We show that models trained with the transformed kref exhibit a 11.6%−68.4% reduction in performance upon re‐conversion to kref compared to those trained with the original kref. The variable importance analysis identifies distinct key predictors governing the original kref and its transformed counterparts. This suggests that data transformation alters the relative significance of predictors without necessarily improving kref prediction performance. Consequently, our study underscores the importance of directly focusing on the original values rather than alternative representations when dissecting a given variable's patterns and mechanisms in ecological modeling. Core Ideas: Data transformation caused reduced predictive performance upon re‐conversion to kref compared to the original kref.Models trained with data transformation exhibited divergent edaphic‐climatic controls for different formatted kref.This study underscores the importance of directly focusing on original values rather than alternative representations. Plain Language Summary: The first‐order model is commonly used to simulate the dynamics of soil organic matter decomposition. The reference decomposition rates (kref) in the first‐order model are usually transformed into reciprocal or logarithmic formats, which may affect model performance as well as the regulatory patterns of edaphic‐climatic factors. In this study, we investigated the effects of data transformation on predictive performance and variable importance. We found that models trained with transformed kref exhibited reduced performance upon re‐conversion to kref, compared to those trained with the original kref. In addition, data transformation altered the distribution and range of the dependent variable, leading to divergent controlling roles of explanatory variables pertaining to models trained with different formatted kref. Our study underscores the need to apply models directly to the original variables rather than their transformed representations. [ABSTRACT FROM AUTHOR]