Diversity-stability relationships in grasslands depend on the environment. Climate change and soil degradation potentially alter soil pH and community stability within grassland environments, although it remains unclear how soil acidity and alkalinity affect diversity-stability relationships. We conducted a three-year experiment of acidification and alkalization treatments in an arid grassland in northern China, and found that increasing and decreasing soil pH reduced community species richness, community diversity, community and dominant species asynchrony, and biomass stability. Soil acidification reduced community stability by reducing dominant species stability. Soil alkalization reduced community stability by reducing species asynchrony and dominant species stability. Acidification significantly enhanced the availabilities of soil NO3—N, P, and K, but did not affect the concentrations of soil total C, N, and P. By contrast, alkalization significantly reduced soil total C and N, but did not affect the availabilities of soil N, P, and K. Structural equation model analysis revealed that altered soil pH affected soil nutrients associated with species asynchrony and community stability, which indicated the importance of soil nutrients in driving community stability. Our results suggest that soil pH–mediated community stability is mainly driven by dominant species stability rather than diversity. This study provides novel insights indicating that arid grassland stability would be weakened under changing soil pH, subsequently leading to land degradation and reducing long‐term productivity and sustainability.

With the rapid and large production of biological data (phenotypic traits, genomes, and simulated DNA), traditional statistic-based approaches may not meet the demands of ecological or evolutionary inferences. To mitigate this issue, we propose supervised visual and statistical machine learning approaches to do biological, evolutionary, and demographic inference. We introduce five supervised learning approaches (DAPC, DAKPC, LFDA, LFDAKPC, KLFDA) into ecology and evolution within the same discriminant analysis family, but with different linear and non-linear properties. We tested their performance and expected to find the optimal method for biological, evolutionary, and demographic inference. Applicable examples of such methods include species classification, population structure identification, and demography inference. We applied these five supervised learning techniques to simulated spatially-structured demographic scenarios along with realistic ecological and genetic data to elucidate their power and practicability in pattern inference. LFDA shows the highest discriminatory power in demographic inference. However, KLFDA outperforms other methods in population structure identification. DAPC and DAKPC differentiated species traits well when applied to real datasets. These approaches assess the structure of the data without model assumptions and show the potential to identify complex demographic histories and subtle population structure. We have made the DA package available at https://github.com/xinghuq/DA. We recommend users choose these machine learning approaches appropriately depending on their scientific questions and target data.