Multiple stable states of tree cover in a global land surface model due to a fire‐vegetation feedback by G. Lasslop, V. Brovkin, C. H. Reick, S. Bathiany, S. Kloster

“…The multiple stable states occur in the transition zones between grasslands and forests, mainly in Africa and Asia. By sensitivity simulations and simplifying the relevant model equations we show that the occurrence of multiple states is caused by the sensitivity of the fire disturbance rate to the presence of woody plant types.…”
Get full text

How to use learning curves to evaluate the sample size for malaria prediction models developed using machine learning algorithms by Sophie G. Zaloumis, Megha Rajasekhar, Julie A. Simpson

“…Results For this mock malaria prediction study, the balanced error rate on a test dataset not used for model training (208 samples) was 50% for sPLSDA + SVMs and 50% for random forests on the smallest training dataset evaluated (20 samples) and 14% for sPLSDA + SVMs and 22% for random forests on the largest training dataset evaluated (835 samples). …”
Get full text

A miR156-SPL module controls shade-induced inhibition of vascular cambium activity through cytokinin pathway in poplar by Hongbin Wei, Xingyue Xiao, Jiao Deng, Yi Li, Mengting Luo, Chengshan Zhang, Jieqiong Li, Jiayi Xu, Keming Luo

“…Summary: In natural forests and plantations, trees often encounter neighbor proximity that hinders wood production. …”
Get full text

OPTIMIZATION STRATEGIES AND COMPUTATIONAL MODELING IN THE DESIGN AND PERFORMANCE EVALUATION OF GREEN POROUS OIL ADSORBENT MATERIALS by Haoran Zhang, Sagdat Mederbekovna Tazhibayeva

“…Based on material properties, artificial neural networks and random forests were trained on experimental and simulated data to predict adsorption capacities and reveal adsorbent material behavior under different conditions. …”
Get full text

OPTIMIZATION STRATEGIES AND COMPUTATIONAL MODELING IN THE DESIGN AND PERFORMANCE EVALUATION OF GREEN POROUS OIL ADSORBENT MATERIALS by Haoran Zhang, Sagdat Mederbekovna Tazhibayeva

“…Based on material properties, artificial neural networks and random forests were trained on experimental and simulated data to predict adsorption capacities and reveal adsorbent material behavior under different conditions. …”
Get full text

Deep Space Insights: Machine Learning Revolutionizing Astrophysical Discoveries by Dutta Samya, Paul Prithwineel

“…Autoencoders and RNNs are used for anomaly detection and time-series analysis, respectively, while GANs enhance the resolution of cosmological simulations. These significant contributions have come through with machine learning concerning galaxy classification, gravitational wave detection, exoplanet detection, and analysis upscaling of N-body simulations and dark matter detection and cosmic expansion. …”
Get full text

Estimation of Evapotranspiration of Amazon Rainforest Using the Maximum Entropy Production Method by Donghui Xu, Elizabeth Agee, Jingfeng Wang, Valeriy Y. Ivanov

“…Abstract Energy budget of Amazonian forests has a large influence on regional and global climate, but relevant data are scarce. …”
Get full text

Current and future land use and land cover scenarios in the Arroio Marrecas watershed by Carlos G. Tornquist, Diego S. da Silva

“…ABSTRACT This study evaluated historic land use and land cover changes in the Arroio Marrecas watershed (Caxias do Sul, Rio Grande do Sul state of Brazil) and simulated future land use scenarios until 2034. Spatial and temporal simulations were conducted with the Conversion of Land Use and its Effects - Small Regional Extent (CLUE-S) model. …”
Get full text

Highly adaptive Lasso for estimation of heterogeneous treatment effects and treatment recommendation by Nizam Sohail, Codi Allison, Rogawski McQuade Elizabeth, Benkeser David

“…Many machine learning-based frameworks for such estimation have been proposed, including meta-learning, causal trees, and causal forests. However, few of these methods are interpretable, while those that do emphasize interpretability often suffer in terms of performance. …”
Get full text

A Three-Component Polarimetric Target Decomposition Algorithm for Grasslands by Baokun Liu, Xiaoqi Lv, Xiujuan Li, Xiangli Yang, Pingping Huang, Weixian Tan, Yongguang Zhai, Yuejuan Chen, Kunpeng Xu

“…Previous polarimetric target decomposition methods have been widely used in forests and buildings and have achieved good results. …”
Get full text

Aero-Engine Fault Detection with an LSTM Auto-Encoder Combined with a Self-Attention Mechanism by Wenyou Du, Jingyi Zhang, Guanglei Meng, Haoran Zhang

“…The dataset utilized in this study was simulated from real data and injected with fault information. …”
Get full text

Impacts of leaf traits on vegetation optical properties in Earth system modeling by Yujie Wang, Renato K. Braghiere, Woodward W. Fischer, Yitong Yao, Zhaoyi Shen, Tapio Schneider, A. Anthony Bloom, David Schimel, Holly Croft, Alexander J. Winkler, Markus Reichstein, Christian Frankenberg

“…Earth System Models (ESMs) typically simulate land surface processes based on plant functional types (PFTs), neglecting the diversity of plant functional traits or characteristics (PFCs; e.g., chlorophyll content and leaf mass per area). …”
Get full text

Treatment Effect Estimation in Survival Analysis Using Copula-Based Deep Learning Models for Causal Inference by Jong-Min Kim

“…In contrast, logistic regression and causal forests produce a substantially smaller estimate, potentially underestimating the treatment effect, particularly in structured datasets such as COMPAS scores. …”
Get full text

Sequestration potential of soil organic carbon under selected land use, land cover and climate change scenarios in Kibwezi West dryland, Eastern Kenya by Anne Monyenye Omwoyo, Richard Ndemo Onwonga, Oliver Vivian Wasonga, Kinyanjui James Mwangi

“…This study assessed the spatial and temporal changes in SOC stocks from four LULC types (cropland, forested land, grassland and shrubland) in Kibwezi West, Kenya. …”
Get full text

Predicting snow structures relevant to reindeer husbandry by Emma T. D. Perkins, Amanda H. Lynch, Vera Solovyeva, David A. Bailey

“…Climate model and detailed snowpack simulations were performed for 1950 to 2100 along the proposed route. …”
Get full text

Productivity and socioeconomic sustainability of Bubalus bubalis in the western lowlands of Venezuela by Carlos Alberto Calles Navas, Verena Torres Cardenas

“…The simulator, built with Microsoft Excel, used the methodology of formulation and evaluation of agricultural investment projects. …”
Get full text

A Tractor Work Position Prediction Method Based on CNN-BiLSTM Under GNSS Signal Denial by Yangming Hu, Liyou Xu, Xianghai Yan, Ningjie Chang, Qigang Wan, Yiwei Wu

“…In farmland environments where GNSS signals are obstructed, such as forested areas or in adverse weather conditions, traditional GNSS/INS integrated navigation systems suffer from positioning errors and instability. …”
Get full text

A comparison of various imputation algorithms for missing data. by Jürgen Kampf, Iryna Dykun, Tienush Rassaf, Amir Abbas Mahabadi

“…The subroutines to be compared are predictive mean matching, weighted predictive mean matching, sampling, classification or regression trees and random forests.<h4>Methods</h4>We compare these subroutines on real data and on simulated data. …”
Get full text

Fitness landscapes of human microsatellites. by Ryan J Haasl, Bret A Payseur

“…Using a random forests approach to approximate Bayesian computation, we fit these models to carefully chosen microsatellites genotyped in 200 humans from a diverse collection of eight populations. …”
Get full text

Mixed effect gradient boosting for high-dimensional longitudinal data by Oyebayo Ridwan Olaniran, Saidat Fehintola Olaniran, Jeza Allohibi, Abdulmajeed Atiah Alharbi, Nada MohammedSaeed Alharbi

“…MEGB provides a unified framework for analysing repeated measures data that accommodates complex covariance structures while harnessing gradient boosting’s inherent regularisation for robust feature selection and prediction. In comprehensive simulations spanning linear and nonlinear data-generating processes, MEGB achieved 35-76% lower mean squared error (MSE) compared to state-of-the-art alternatives like Mixed-Effect Random Forests (MERF) and REEMForest, while maintaining 55-70% true positive rates for variable selection in ultra-high-dimensional regimes $$(p=2000)$$ ( p = 2000 ) . …”
Get full text