Random Forest Regression Analysis Research Articles

Bioinformatics identification and validation of maternal blood biomarkers and immune cell infiltration in preeclampsia: An observational study.

Preeclampsia (PE) is a pregnancy complication characterized by placental dysfunction. However, the relationship between maternal blood markers and PE is unclear. It is helpful to improve the diagnosis and treatment of PE using new biomarkers related to PE in the blood. Three PE-related microarray datasets were obtained from the Gene Expression Synthesis database. The limma software package was used to identify differentially expressed genes (DEGs) between PE and control groups. Least absolute shrinkage and selection operator regression, support vector machine, random forest, and multivariate logistic regression analyses were used to determine key diagnostic biomarkers, which were verified using clinical samples. Subsequently, functional enrichment analysis was performed. In addition, the datasets were combined for immune cell infiltration analysis and to determine their relationships with core diagnostic biomarkers. The diagnostic performance of key genes was evaluated using the receiver operating characteristic (ROC) curve, C-index, and GiViTi calibration band. Genes with potential clinical applications were evaluated using decision curve analysis (DCA). Seventeen DEGs were identified, and 6 key genes (FN1, MYADM, CA6, PADI4, SLC4A10, and PPP4R1L) were obtained using 3 types of machine learning methods and logistic regression. High diagnostic performance was found for PE through evaluation of the ROC, C-index, GiViti calibration band, and DCA. The 2 types of immune cells (M0 macrophages and activated mast cells) were significantly different between patients with PE and controls. All of these genes except SLC4A10 showed significant differences in expression levels between the 2 groups using quantitative reverse transcription-polymerase chain reaction. This model used 6 maternal blood markers to predict the occurrence of PE. The findings may stimulate ideas for the treatment and prevention of PE.

Unraveling Endometrial Cancer Survival Predictors Through Advanced Machine Learning Techniques.

This study explores endometrial cancer (EC) within the broader context of oncogynecology, focusing on 3,845 EC patients at the Almazov National Research Center. The research analyzes clinical data, employing machine learning techniques like random forest regression and decision tree analysis. Key findings include age-dependent impacts on EC outcomes, unexpected correlations between dietary habits and recurrence risk (e.g., higher risk for vegans), and intriguing associations like soft drink consumption influencing relapse. Despite limitations like a retrospective design and self-reported data, the study's extended eight-year follow-up and robust database enhance its credibility. The nuanced insights into EC risk factors, influenced by factors like physical activity and diet, open avenues for targeted diagnostics and prevention strategies, showcasing the potential of machine learning in predicting outcomes.

Mortality prediction and influencing factors for intensive care unit patients with acute tubular necrosis: random survival forest and cox regression analysis

Background: Patients with acute tubular necrosis (ATN) not only have severe renal failure, but also have many comorbidities, which can be life-threatening and require timely treatment. Identifying the influencing factors of ATN and taking appropriate interventions can effectively shorten the duration of the disease to reduce mortality and improve patient prognosis.Methods: Mortality prediction models were constructed by using the random survival forest (RSF) algorithm and the Cox regression. Next, the performance of both models was assessed by the out-of-bag (OOB) error rate, the integrated brier score, the prediction error curve, and area under the curve (AUC) at 30, 60 and 90 days. Finally, the optimal prediction model was selected and the decision curve analysis and nomogram were established.Results: RSF model was constructed under the optimal combination of parameters (mtry = 10, nodesize = 88). Vasopressors, international normalized ratio (INR)_min, chloride_max, base excess_min, bicarbonate_max, anion gap_min, and metastatic solid tumor were identified as risk factors that had strong influence on mortality in ATN patients. Uni-variate and multivariate regression analyses were used to establish the Cox regression model. Nor-epinephrine, vasopressors, INR_min, severe liver disease, and metastatic solid tumor were identified as important risk factors. The discrimination and calibration ability of both predictive models were demonstrated by the OOB error rate and the integrated brier score. However, the prediction error curve of Cox regression model was consistently lower than that of RSF model, indicating that Cox regression model was more stable and reliable. Then, Cox regression model was also more accurate in predicting mortality of ATN patients based on the AUC at different time points (30, 60 and 90 days). The analysis of decision curve analysis shows that the net benefit range of Cox regression model at different time points is large, indicating that the model has good clinical effectiveness. Finally, a nomogram predicting the risk of death was created based on Cox model.Conclusion: The Cox regression model is superior to the RSF algorithm model in predicting mortality of patients with ATN. Moreover, the model has certain clinical utility, which can provide clinicians with some reference basis in the treatment of ATN and contribute to improve patient prognosis.

Integrated analysis reveals critical cisplatin-resistance regulators E2F7 contributed to tumor progression and metastasis in lung adenocarcinoma

BackgroundDrug resistance poses a significant challenge in cancer treatment, particularly as a leading cause of therapy failure. Cisplatin, the primary drug for lung adenocarcinoma (LUAD) chemotherapy, shows effective treatment outcomes. However, the development of resistance against cisplatin is a major obstacle. Therefore, identifying genes resistant to cisplatin and adopting personalized treatment could significantly improve patient outcomes.MethodsBy examining transcriptome data of cisplatin-resistant LUAD cells from the GEO database, 181 genes associated with cisplatin resistance were identified. Using univariate regression analysis, random forest and multivariate regression analyses, two prognostic genes, E2F7 and FAM83A, were identified. This study developed a prognostic model utilizing E2F7 and FAM83A as key indicators. The Cell Counting Kit 8 assay, Transwell assay, and flow cytometry were used to detect the effects of E2F7 on the proliferation, migration, invasiveness and apoptosis of A549/PC9 cells. Western blotting was used to determine the effect of E2F7 on AKT/mTOR signaling pathway.ResultsThis study has pinpointed two crucial genes associated with cisplatin resistance, E2F7 and FAM83A, and developed a comprehensive model to assist in the diagnosis, prognosis, and evaluation of relapse risk in LUAD. Analysis revealed that patients at higher risk, according to these genetic markers, had elevated levels of immune checkpoints (PD-L1 and PD-L2). The prognostic and diagnosis values of E2F7 and FAM83A were further confirmed in clinical data. Furthermore, inhibiting E2F7 in lung cancer cells markedly reduced their proliferation, migration, invasion, and increased apoptosis. In vivo experiments corroborated these findings, showing reduced tumor growth and lung metastasis upon E2F7 suppression in lung cancer models.ConclusionOur study affirms the prognostic value of a model based on two DEGs, offering a reliable method for predicting the success of tumor immunotherapy in patients with LUAD. The diagnostic and predictive model based on these genes demonstrates excellent performance. In vitro, reducing E2F7 levels shows antitumor effects by blocking LUAD growth and progression. Further investigation into the molecular mechanisms has highlighted E2F7’s effect on the AKT/mTOR signaling pathway, underscoring its therapeutic potential. In the era of personalized medicine, this DEG-based model promises to guide clinical practice.

Melatonin promotes the recovery of apple plants after waterlogging by shaping the structure and function of the rhizosphere microbiome.

The dynamics of the physiological adaptability of plants and the rhizosphere soil environment after waterlogging remain unclear. Here we investigated the mechanisms regulating plant condition and shaping of the rhizosphere microbiome in a pot experiment. In the experiment, we added melatonin to waterlogged plants, which promoted waterlogging relief. The treatment significantly enhanced photosynthesis and the antioxidant capacity of apple plants, and significantly promoted nitrogen (N) utilization efficiency by upregulating genes related to N transport and metabolism. Multiperiod soil microbiome analysis showed the dynamic effects of melatonin on the diversity of the microbial community during waterlogging recovery. Random forest and linear regression analyses were used to screen for potential beneficial bacteria (e.g., Azoarcus, Pseudomonas and Nocardioides) specifically regulated by melatonin and revealed a positive correlation with soil nutrient levels and plant growth. Furthermore, metagenomic analyses revealed the regulatory effects of melatonin on genes involved in N cycling in soil. Melatonin positively contributed to the accumulation of plant dry weight by upregulating the expression of nifD and nifK (N fixation). In summary, melatonin positively regulates physiological functions in plants and the structure and function of the microbial community; it promoted the recovery of apple plants after waterlogging stress.

Root Respiration–Trait Relationships Are Influenced by Leaf Habit in Tropical Plants

Root respiration is a critical physiological trait that significantly influences root system activity. Recent studies have associated root respiration with the economic functioning of roots; however, research on root respiration in tropical plants remains limited. This study examined the fine root respiration and the relationship between root respiration and root chemical and morphological traits in 16 tropical plant species, including both evergreen and deciduous species. Findings revealed that deciduous species exhibited higher root respiration compared to evergreen species. Root respiration positively correlated with root nitrogen concentration and specific root length and correlated negatively with root diameter and root tissue density across all species. The root respiration patterns in evergreen species aligned with those seen in all tree species, while deciduous species showed a distinct negative correlation with root tissue density and no significant correlations with other root traits. Principal component analysis revealed that the patterns of root variation in both evergreen and deciduous trees were multidimensional, with deciduous trees exhibiting acquisitive traits and evergreen trees displaying conservative traits. Random forest and multiple regression analysis showed that specific root length exerted the most significant influence on root respiration in both evergreen and deciduous trees. These findings are ecologically significant, enhancing our understanding of root respiration in tropical plants and its impact on ecosystem functions. They contribute valuable insights and support the conservation and management of tropical vegetation.

Exploring the drivers of local government budget coordination: A random forest regression analysis

Budget coordination is a critical issue of local government coordinative governance. Existing literature emphasizes its importance but does not give in-depth empirical research. The random forest regression model was used to probe into the drivers of budget coordination for 2815 local government projects in China. Based on the purity of the split nodes of the decision tree, the three most important factors for achieving the goal of local government budget coordination are identified: discretion, decision-making level and fund scale. The partial dependence graphs visually illustrate the differentiated and nonlinear marginal effects of various explanatory variables on the response variable.

Exploring the NRF2-TP53 Signaling Network Through Machine Learning and Pan-Cancer Analysis: Identifying Potential targets for Cancer Prognosis Related to Oxidative Stress.

Oxidative stress (OXS) is closely related to tumor prognosis and immune response, while TP53 integrated with NRF2 is closely associated with the regulation of cancer-related OXS. Hence, constructing a TP53-NRF2 integrated OXS signature of pan-cancer is essential in predicting survival prognosis and facilitating cancer drug treatment. The pan-cancer analysis acquired the Cancer Genome Atlas (TCGA) transcriptome sequencing data from UCSC Xena, which consisted of 33 cancer types (n = 10440). The Random Forest, Lasso regression, and Cox regression analyses are used to construct an OXS score based on 25 OXS genes. Following this, based on the OXS signature, patients are categorized into low- and high-risk groups. The disparities between the two cohorts regarding survival prognosis, immune infiltration, and drug sensitivity are delved deeply. The expression level of genes is confirmed using immunohistochemistry. The prognosis of pan-cancer patients is adequately predicted by the OXS signature with the assistance of the machine-learning algorithm. A highly accurate nomogram is developed by combining the OXS signature and clinical features. The presence of immune cells indicated that the OXS signature can be associated with the critical pathways of immunotherapy for all types of cancer, and BCL2 showed promising results. Distinct inter-group differences are observed in the OXS signature for frequently utilized antineoplastic medications in clinical settings, including first-line drugs suggested in the guidelines. In summary, by conducting a thorough analysis of OXS genes, a new model based on OXSscore is successfully developed. This model can predict the clinical prognosis and drug sensitivity of pan-cancer with high accuracy. Potential stars in the field of cancer-related anti-OXS may include drugs that target BCL2.

Spatiotemporal drivers of urban water pollution: Assessment of 102 cities across the Yangtze River Basin

Effective management of large basins necessitates pinpointing the spatial and temporal drivers of primary index exceedances and urban risk factors, offering crucial insights for basin administrators. Yet, comprehensive examinations of multiple pollutants within the Yangtze River Basin remain scarce. Here we introduce a pollution inventory for urban clusters surrounding the Yangtze River Basin, analyzing water quality data from 102 cities during 2018–2019. We assessed the exceedance rates for six pivotal indicators: dissolved oxygen (DO), ammonia nitrogen (NH3–N), chemical oxygen demand (COD), biochemical oxygen demand (BOD), total phosphorus (TP), and the permanganate index (CODMn) for each city. Employing random forest regression and SHapley Additive exPlanations (SHAP) analyses, we identified the spatiotemporal factors influencing these key indicators. Our results highlight agricultural activities as the primary contributors to the exceedance of all six indicators, thus pinpointing them as the leading pollution source in the basin. Additionally, forest coverage, livestock farming, chemical and pharmaceutical sectors, along with meteorological elements like precipitation and temperature, significantly impacted various indicators' exceedances. Furthermore, we delineate five core urban risk components through principal component analysis, which are (1) anthropogenic and industrial activities, (2) agricultural practices and forest extent, (3) climatic variables, (4) livestock rearing, and (5) principal polluting sectors. The cities were subsequently evaluated and categorized based on these risk components, incorporating policy interventions and administrative performance within each region. The comprehensive analysis advocates for a customized strategy in addressing the discerned risk factors, especially for cities presenting elevated risk levels.

Prediction Method for High-Speed Laser Cladding Coating Quality Based on Random Forest and AdaBoost Regression Analysis.

The initial melting quality of a high-speed laser cladding layer has an important impact on its post-treatment and practical application. In this study, based on the repair of hydraulic support columns of coal mining machines, the influence of high-speed laser cladding process parameters on the quality of Fe-Cr-Ni alloy coatings was investigated to realize the accurate prediction of coating quality. The Taguchi orthogonal method was used to design the L25(56) test. The prediction models of the relationship between the cladding process and the coating quality were established using the Random Forest (RF) and AdaBoost (Adaptive Boosting, AB) algorithms, respectively. Then, the prediction accuracy of the two models was compared, and the process parameter features were screened for importance evaluation. The results show that the AB prediction model is more accurate than the RF prediction model and more sensitive to abnormal data. The importance evaluation based on the AdaBoost model shows that the scanning speed has a great influence on the height and surface roughness of the coating. On the other hand, the overlap rate is the most important factor in controlling the dilution ratio and near-surface grain size of high-speed laser melting coatings. In addition, the micro-hardness of the coating and the thermal effect of the substrate can be effectively enhanced by adjusting the laser power and scanning speed. Finally, it was verified that the AB prediction model could accurately estimate the quality indexes of the coating with a prediction error less than 6%. The results show that it is feasible to predict the quality of high-speed laser cladding with the AB algorithm. It provides a basis for the adjustment of process parameters in the subsequent quality control process of cladding.

Dynamic Survival Risk Prognostic Model and Genomic Landscape for Atypical Teratoid/Rhabdoid Tumors: A Population-Based, Real-World Study.

An atypical teratoid/rhabdoid tumor (AT/RT) is an uncommon and aggressive pediatric central nervous system neoplasm. However, a universal clinical consensus or reliable prognostic evaluation system for this malignancy is lacking. Our study aimed to develop a risk model based on comprehensive clinical data to assist in clinical decision-making. We conducted a retrospective study by examining data from the Surveillance, Epidemiology, and End Results (SEER) repository, spanning 2000 to 2019. The external validation cohort was sourced from the Children's Hospital Affiliated to Chongqing Medical University, China. To discern independent factors affecting overall survival (OS) and cancer-specific survival (CSS), we applied Least Absolute Shrinkage and Selection Operator (LASSO) and Random Forest (RF) regression analyses. Based on these factors, we structured nomogram survival predictions and initiated a dynamic online risk-evaluation system. To contrast survival outcomes among diverse treatments, we used propensity score matching (PSM) methodology. Molecular data with the most common mutations in AT/RT were extracted from the Catalogue of Somatic Mutations in Cancer (COSMIC) database. The annual incidence of AT/RT showed an increasing trend (APC, 2.86%; 95% CI:0.75-5.01). Our prognostic study included 316 SEER database participants and 27 external validation patients. The entire group had a median OS of 18 months (range 11.5 to 24 months) and median CSS of 21 months (range 11.7 to 29.2). Evaluations involving C-statistics, DCA, and ROC analysis underscored the distinctive capabilities of our prediction model. An analysis via PSM highlighted that individuals undergoing triple therapy (integrating surgery, radiotherapy, and chemotherapy) had discernibly enhanced OS and CSS. The most common mutations of AT/RT identified in the COSMIC database were SMARCB1, BRAF, SMARCA4, NF2, and NRAS. In this study, we devised a predictive model that effectively gauges the prognosis of AT/RT and briefly analyzed its genomic features, which might offer a valuable tool to address existing clinical challenges.

Gut microbiota was highly related to the immune status in chronic obstructive pulmonary disease patients.

This study aimed to explore the profile of gut microbiota and immunological state in COPD patients. 80 fecal and blood samples were collected from 40 COPD patients and 40 healthy controls (HC) and analyzed with 16s-rRNA gene sequencing and immunofactor omics analysis to investigate the profile of gut microbiota and immunologic factors (IFs). The linear discriminant analysis (LDA) effect size (LefSe) was used to determine the biomarker's taxa. The random forest and LASSO regression analysis were executed to screen IFs and develop an IFscore model. The correlation between gut microbiota and IFs, along with the IFscore and the diversity of gut microbiota, was evaluated with the Spearman analysis. The α and β diversity showed that the composition and distribution of gut microbiota in the COPD group differed from that of the HC group. 7 differential taxa at the phylum level and 17 differential taxa at the genus level were found. LefSe analysis screened out 5 biomarker's taxa. 32 differential IFs (up-regulated 27 IFs and down-regulated 5 IFs) were identified between two groups, and 5 IFs (CCL3, CXCL9, CCL7, IL2, IL4) were used to construct an IFscore model. The Spearman analysis revealed that 29 IFs were highly related to 5 biomarker's taxa and enriched in 16 pathways. Furthermore, the relationship between the IFscore and gut microbiota diversity was very close. The gut microbiota and IFs profile in COPD patients differed from that in healthy individuals. Gut microbiota was highly related to the immune status in COPD patients.

Characterization of controlling factors for soil organic carbon stocks in one Karst region of Southwest China.

Soil organic carbon (SOC) contributes the most significant portion of carbon storage in the terrestrial ecosystem. The potential for variability in carbon losses from soil can lead to severe consequences such as climate change. While extensive studies have been conducted to characterize how land cover type, soil texture, and topography impact the distribution of SOC stocks across different ecosystems, little is known about in Karst Region. Here, we characterized SOC stocks with intensive sampling at the local scale (495 representative samples) via Random Forest Regression (RF) and Principal Component Analysis (PCA). Our findings revealed significant differences in SOC stock among land cover types, with croplands exhibiting the lowest SOC stocks, indicating that management practices could play a crucial role in SOC stocks. Conversely, there was little correlation between SOC stock and clay percentage, suggesting that soil texture was not a primary factor influencing SOC at a local scale. Further, Annual Precipitation was identified as the key driving factor for the dynamics of SOC stocks with the help of RF and PCA. A substantial SOC deficit was observed in most soils in this study, as evaluated by a SOC/clay ratio, indicating a significant potential in SOC sequestration with practical measures in the karst region. As such, future research focused on simulating SOC dynamics in the context of climate change should consider the controlling factors at a local scale and summarize them carefully during the up-scaling process.

Aggregating Synechococcus contributes to particle organic carbon export in coastal estuarine waters: Its lineage features and assembly processes

The release and deposition of phytoplankton-derived particulate organic matter is crucial in marine carbon export, yet the roles of picoplankton in these processes were seldom considered. Therefore, this study aimed to shed light on the matter by investigating the aggregating (AG) lifestyle of Synechococcus, a main group of picoplankton, in the coastal waters of the Yellow River Estuary with ample sediments acting as ballast minerals. We revealed that AG Synechococcus constituted a substantial portion, maximally reaching up to 85.4 %, of the total Synechococcus population. Pearson correlations and random forest (RF) regression analyses found significant connections (p < 0.01) between AG Synechococcus and the content of particulate organic carbon (POC), which emphasized its underlying role in facilitating POC export in this region. Furthermore, by employing high-throughput sequencing of the RNA polymerase gene (rpoC1), it was demonstrated that S5.1 clade I exhibited a significantly higher proportion in the AG fraction than in the free-living (FL) fraction (p < 0.05). This suggests distinct inclinations in the phylogenetic preference for different Synechococcus lineages between different lifestyles in the studied area. Finally, we ascertained “small-world” and higher robustness attributes of aggregates formed through the co-occurrence construction between Synechococcus and heterotrophic bacteria, likely facilitated by the reciprocal exchange of carbon and nitrogen elements. Overall, these findings have implications for our understanding of the role of Synechococcus in the ecology and biogeochemistry of marine ecosystems, and they are significant for more accurately evaluating the contribution of picophytoplankton in ocean carbon export.

Global zenith wet delay modeling with surface meteorological data and machine learning

The tropospheric delay is a major error source for space geodetic techniques, and the performance of its modeling is significantly limited due to the high spatiotemporal variability of the moisture in the lower atmosphere. In this study, global modeling of the tropospheric zenith wet delay (ZWD) was realized based on surface meteorological data obtained from radiosondes and Global Positioning System (GPS) radio occultation (RO) measurements through the random forest (RF) and backpropagation neural network (BPNN) regression analysis. The modeling performance was further validated based on two kinds of global atmospheric profiles for the year 2020. Our results show that the ZWD modeling accuracy gained by two machine learning regression approaches is significantly improved by taking into account surface meteorological parameters, especially the surface water vapor pressure when compared to the Global Pressure and Temperature 3 (GPT3) model. When surface meteorological data are available, the RF-B model yields ZWD estimations with an overall agreement of 3.1 cm in comparison with the sounding profiles and 2.4 cm in contrast to the GPS RO atmospheric profiles. The RF-B is superior to other models based on surface meteorological parameters for ZWD calculation, e.g., the accuracy improves by 21.8–23.8% against the approach by Saastamoinen and 7–12.2% against the formula by Askne and Nordius.

CRYL1 is a Potential Prognostic Biomarker of Clear Cell Renal Cell Carcinoma Correlated with Immune Infiltration and Cuproptosis.

Clear cell renal cell carcinoma (ccRCC) is a widespread urogenital neoplasm. However, the therapeutic efficacy of these methods is unsatisfactory. In-depth screening of biomarkers could aid early diagnosis and therapy and predict patient prognosis. The GEO datasets were selected with specific criteria. Differentially expressed gene (DEG), weighted gene coexpression network analysis (WGCNA), protein-protein interaction, LASSO, random forest, and Cox regression analyses were applied to identify the independent prognostic biomarkers. Survival analysis, correlation with clinical features, gene set enrichment analysis (GSEA), GO enrichment, immune infiltration analysis, and correlation with cuproptosis-related genes were carried out to determine the prognostic value and possible molecular mechanisms of the TSVR. Wound healing assays, transwell assays, cell colony formation experiments, flow cytometry, and immunohistochemistry (IHC) analysis were used to validate the functional attributes of CRYL1. Four GEO datasets were included to screen for hub genes. DEG combined with WGCNA showed a key module with 300 genes having the strongest correlation with "survival state" (R2 = -0.24 and P = 7e-8); six genes were identified by LASSO, random forest, and Cytoscape. Finally, CRYL1 (hazard ratio (HR) = 2.01, P < 0.001) was selected as an independent prognostic biomarker. The higher CRYL1 expression group had better DFS and overall survival (OS). GSEA demonstrated that the CRYL1-related DEGs were enriched mainly in the metabolism of sugar, fat, and amino acids. CRYL1 is positively correlated with FDX1 and the LIAS pathway, which are important molecule involved in cuproptosis. CRYL1 affects the infiltration abundance of four immune cells and can predict a positive OS. Wound healing, transwell, cell colony formation, and flow cytometry assays demonstrated that CRYL1 silencing enhances migration and proliferation and leads to a decreased apoptotic ratio. IHC analysis suggested that CRYL1 was highly expressed in adjacent tissues. CRYL1 is a robust predictive marker for clinicopathological characteristics and survival status in ccRCC patients.

Soil multifunctionality predicted by bacterial network complexity explains differences in wheat productivity induced by fertilization management

Fertilization will cause changes in crop growth, soil microbial community and multiple ecosystem functions, but it is unclear whether and how the optimal productivity obtained by manure application and optimizing nitrogen is driven by microbial community and ecosystem multifunctionality. We explore this mechanism based on a field fertilization experiment using a split-plot design that began in 2014 with five N rates (N0, N75, N150, N225, N300) as main plots and two manure rates (M0, NPK group; M1, MNPK group) as subplots, respectively. In general, (1) grain yield was parabolically related to the N application rate. The N rates that obtained the highest yield were 150 kg ha−1 and 225 kg ha−1 for the MNPK and NPK groups, respectively. The average yield of the MNPK group was 10.5% higher than that of the NPK group. (2) Long-term fertilization management resulted in regular changes in soil multifunctionality (SMF) and the properties of various microbial communities. The richness, network complexity and soil multifunctionality of bacterial and fungal communities also increased initially and then decreased as the N rate. On average, the response ratio of soil multifunctionality to N75, N150, N225, N300 (control is N0) and M1 (control is M0) were 0.11, 0.41, 0.53, 0.44 and 1.19, respectively. The soil multifunctionality of MNPK was 260%, 722% and 101% higher than that of NPK at the tillering, jointing and harvest stages, respectively. (3) Soil multifunctionality not only always had a significant positive effect on aboveground biomass at all growth stages, but also had significant positive correlations with bacterial richness and network complexity. Based on the existing framework, we further demonstrated that high microbial richness supports multifunctionality by ensuring strong associative complexity among microorganisms. However, only bacterial network complexity always positively drove soil multifunctionality and indirectly influenced wheat growth at all growth stages in SEMs where multiple drivers were considered simultaneously (i.e., pH, SOC and biological factors). Random forest regression analysis showed that rare bacterial taxa had stronger predictive effects on soil multifunctionality than abundant taxa. Our results validate that M1N150 can ensure high yield in the study area while maintaining a high level of ecosystem function in the soil, which also contributes to the reduction of adverse environmental risks caused by fertilizer application. Importantly, the potential of microbial network complexity, especially bacterial network complexity, to influence crop growth by driving farmland ecosystem functions deserves to be explored under different crop types, cropping systems, and irrigation conditions, compared to previous microbial richness that has been simply quantified.

Transformative Trends in Runoff and Sediment Dynamics and Their Influential Drivers in the Wuding River Basin of the Yellow River: A Comprehensive Analysis from 1960 to 2020

The correlation between runoff and sediment challenges ecological preservation and sustainable development in the Yellow River Basin. An understanding of the key factors influencing variations in runoff and sediment transport in crucial river basins is essential for effective soil erosion management within the context of ecological and economic development. The Mann–Kendall test, Pettitt test, and Morlet wavelet analysis were employed in the Wuding River Basin to analyze the trends in runoff and sediment changes from 1960 to 2020. We explored the double cumulative curve method to assess the contribution rates of precipitation and human activities to the variability of runoff and sediment transport. We explored the primary factors driving the changes in runoff and sediment transport through random forest regression analysis. (1) From 1960 to 2020, annual precipitation in the Wuding River Basin increased minimally, while annual runoff and sediment transport decreased strongly with abrupt changes. Abrupt changes in annual runoff and sediment transport occurred in 1971 and 1979, respectively. (2) The relationship between runoff and sediment transport changed in approximately 1972 and 2000. The distribution of monthly runoff became more uniform during Periods II (1973–2001) and III (2002–2020) compared to that during the baseline period (1960–1972, Period I), while sediment transport became increasingly concentrated in the flood season. (3) During Period II, the contribution rates of climate and human activities to runoff and sediment transport were 11.94% and −14.5%, respectively, compared to the baseline period. During Period III, the contribution rates of climate and human activities to runoff and sediment transport were −11.9% and −17.7%, respectively. Human activities substantially reduced runoff and sediment, with greater impacts on sediment reduction. Climate weakly influenced basin sediment transport variations. (4) The normalized difference vegetation index (NDVI) and grassland area extent had the greatest impact on runoff, while the NDVI and forest area extent affected sediment transport.

Community-based plant diversity monitoring of a dense-canopy and species-rich tropical forest using airborne LiDAR data

Tropical forests are widely regarded as the Earth’s most important ecosystems, yet they are severely threatened by anthropogenic disturbances. Rapid and extensive monitoring of forest structure and biodiversity is crucial for developing ecologically sound conservation and restoration strategies. Airborne light detection and ranging (LiDAR) can effectively monitor three-dimensional forest canopy structures. Traditionally, LiDAR-based plant diversity estimation has relied on individual tree-based and area-based approaches. However, these approaches face significant challenges in tropical forests due to their complex canopy structures and diverse plant compositions. Therefore, by proposing a novel community-based approach, this study aims to examine the relationship between field-derived biodiversity indices and LiDAR-derived canopy structural metrics of plant communities in a species-rich ForestGEO forest dynamic plot in tropical Hong Kong. Our goal is to determine whether canopy structural metrics extracted from airborne LiDAR data can serve as a robust and efficient alternative for expediting plant diversity monitoring in highly dense and diverse tropical forests. Our results indicate that an integration watershed segmentation technique (for automatic patch-scale plant community delineation), LiDAR-derived canopy structural metrics, and machine learning-based random forest regression analysis can provide accurate predictions of community-based species diversity indices. Among various diversity indices, species richness and the Shannon-Wiener index are most accurately estimated using LiDAR-derived metrics. This study reveals that species richness is predominantly influenced by the existence of multi-layered canopy structures, whereas the Shannon-Wiener index is associated with both multi-layered structures and canopy morphologies. Overall, our findings showcase the immense potential of airborne LiDAR data in advancing the monitoring of structure and biodiversity in dense-canopy and species-rich tropical forests in a spatially explicit manner.

Toward the design of graft-type proton exchange membranes with high proton conductivity and low water uptake: A machine learning study

Proton conductivity (σ) and hydration number (λ) are important characteristics for proton exchange membranes (PEMs) in fuel cells and water electrolyzers. A High σ yields high performance of these systems, while a low λ improves the dimensional stability to achieve the long-term operation. Accordingly, σ/λ is the most important characteristic because it reflects how efficiently protons can conduct at low water content and is called conduction efficiency in this study. For graft-type PEMs based on various types of polymers, σ, λ, and σ/λ depend on the base polymers, even at the same volume-normalized ion exchange capacity. We analyzed these three characteristics as objective variables using machine learning methods: least absolute shrinkage and selection operator (LASSO), artificial neural network (ANN), and random forest (RF) regression. A total of 20 physical and chemical properties of base polymers collected by literature, experiments, quantum chemical calculation, and descriptor generators were used as explanatory variables. The prediction accuracy was sufficiently high in the ANN and RF regression analyses, and low in LASSO. Only the RF regression model revealed the importance of explanatory variables. It is clear from the RF model that the enhancement of σ/λ should be achieved using base polymers with low crystallinity and high melting point.