Study uses satellite and lidar data to map forest height and biomass in France.
problem Mapping forest resources and carbon in large areas.
method Machine learning approach using Sentinel-1, Sentinel-2, ALOS-2, and GEDI Lidar data.
result High-resolution maps of forest height and biomass produced with good accuracy.
Mapping AGB in French Guiana combines remote sensing and environmental data.
problem Mapping high AGB values in tropical forests is challenging due to signal saturation and lack of calibration data.
method Developed a calibrated regression model using GLAS, forest inventories, and environmental variables.
result Predictive models for AGB in French Guiana have an RMSE of ~51 Mg/ha and R²=0.48 at 1-km grid size.
Method improves microbial biomass yield estimation from noisy data.
problem Estimating microbial biomass yields from noisy cell counts and substrate measurements.
method Probabilistic macrochemical modeling to relax cell weight assumptions and improve robustness.
result Model provides accurate uncertainty estimates of key parameters.
Using the formalism of Lyapunov potential function it is shown that the stability principles for biomass in the ecosystem and for employment in economics are mathematically similar. The ecosystem is found to have a stable and an unstable stationary state with high (forest) and low (grasslands) biomass, respectively. In…
Tuna-AI uses ML to predict tuna biomass from oceanography and echo-sounder data.
problem Estimating tuna biomass from limited data sources.
method Developed a Machine Learning model using 3-day echo-sounder data and oceanographic data.
result Tuna-AI predicts tuna biomass with high accuracy using a 3-day window of data.
In this paper, we consider the classic measurement error regression scenario in which our independent, or design, variables are observed with several sources of additive noise. We will show that our motivating example's replicated measurements on both the design and dependent variables may be leveraged to enhance a spa…
Study analyzes impacts of COVID-19 on French forestry sector, finds mixed results in supply chain.
problem Impact of COVID-19 on forestry sector supply chain and future opportunities.
method Integrated methodology combining Material Flow Analysis and Wood Product Model.
result Significant disruptions and shifts in wood production, highlighting resilience and vulnerabilities.
Automated system identifies and counts insects from images.
problem Manual sorting and identification of insect samples is time-consuming and limits biodiversity mapping.
method Robot-enabled image-based identification machine using CNNs.
result Classification accuracy of 0.980 for initial dataset. Deep RL finds efficient pathways for sugar to chemicals.
problem Finding efficient pathways from sugar to value-added chemicals.
method Markov decision process with deep reinforcement learning.
result Promising preliminary results in efficient biomass conversion.
New methods for predicting compositional data using conformal prediction.
problem No well-established methods for constructing valid prediction sets in compositional data.
method Investigated three conformal prediction-based approaches for Dirichlet regression models.
result HDR approximation approach is robust in terms of coverage, while grid discretization reduces overcoverage.
Model predicts one-year NDVI for Four Corners region.
problem Long-term forecasting of vegetation conditions using climate attributes.
method Two-phase machine learning model using historical climate data.
result Open-source tools outperform alternative methods for NDVI forecasts.
Dynamic programming helps manage fisheries affected by random disturbances.
problem Managing fisheries affected by random disturbances.
method Dynamic programming approach to analyze and optimize management strategies.
result Dynamic programming is crucial for fully characterizing optimal harvest strategies.
Framework generates realistic crop images for growth modeling.
problem Modeling crop growth over time with precision and detail.
method Two-stage framework: image prediction and growth estimation models.
result Framework accurately predicts crop images with varying conditions.
iMondrian forest combines isolation forest and Mondrian forest for better anomaly detection.
problem Anomaly detection in batch and online settings.
method Hybrid of isolation forest and Mondrian forest, using depth in Mondrian forest structure.
result iMondrian forest outperforms existing methods in batch and online settings.
Random Hinge Forests are a new decision forest method that can be integrated into neural networks.
problem Training and optimizing neural networks efficiently and effectively.
method Random Hinge Forests are a novel variant of decision forests that can be integrated into neural networks and optimized end-to-end.
result Random Hinge Forests can be efficiently optimized end-to-end with stochastic gradient descent.
Ensembles of randomized decision trees, usually referred to as random forests, are widely used for classification and regression tasks in machine learning and statistics. Random forests achieve competitive predictive performance and are computationally efficient to train and test, making them excellent candidates for r…
The paper assesses how different parts of random forests influence their performance.
problem Quantifying the impact of each component of random forests on their performance.
method Focuses on simple pure forests and 'hold-out' random forests.
result It is possible to quantify the impact of each ingredient of random forests on their performance.
HDI-Forest improves regression prediction intervals using Random Forest.
problem Improving the quality of prediction intervals in regression tasks.
method HDI-Forest is a novel quality-based PI estimation method based on Random Forest, optimizing PI quality metrics directly from standard tree-based models.
result HDI-Forest significantly reduces PI width by over 20% compared to previous methods, while maintaining or improving coverage probability.
New random forest method provides optimal rates and confidence bands.
problem Improving random forest regression rates and constructing confidence bands.
method Proposed Ehrenfest centered purely random forests achieve optimal rates; used Gaussian approximation for supremum of empirical processes.
result Explicit asymptotic uniform confidence bands constructed for both random forest types.
RFpredInterval package builds prediction intervals for random forests and boosted forests.
problem Quantifying uncertainty in random forest and boosted forest point predictions.
method 16 methods to build prediction intervals with random forests and boosted forests.
result The proposed method outperforms existing methods in building prediction intervals.
Boosting random forests reduces bias and improves predictive performance.
problem Reducing bias in random forest predictions.
method Extract residuals from random forest, fit another random forest to residuals, sum predictions.
result One-step boosted forest has reduced bias and improved predictive performance.
Improved random forest proximities capture data geometry.
problem Inaccurate random forest proximities do not reflect learned data geometry.
method Introduce RF-GAP: Geometry- and Accuracy-Preserving proximities.
result RF-GAP improves geometric representation in tasks like data imputation.
Deep forests enhance expressiveness exponentially with depth, not width or tree size.
problem Understanding the role of depth, width, and tree size in deep forest performance.
method Provided upper and lower bounds on deep forest approximation complexity.
result Depth exponentially enhances deep forest expressiveness.
This paper improves forest pruning to balance accuracy and interpretability.
problem Limited interpretability of regression forests.
method Lasso-pruning and theoretical analysis of regression forests.
result Pruned regression forests can achieve equal or better accuracy than unpruned ones, with significant size reduction.
Forest-guided smoothing uses random forest outputs for interpretable local smoothers.
problem Creating interpretable local smoothers from complex random forest outputs.
method Uses random forest outputs to define spatially adaptive bandwidth matrices for a linear smoother.
result Improves interpretability and applicability of random forest outputs for various analyses.
This paper studies Mondrian Forests, proving they achieve optimal rates in arbitrary dimensions.
problem Understanding optimal rates for Mondrian Forests in arbitrary dimensions.
method Theoretical study based on new results about Mondrian partitions.
result Mondrian Forests achieve minimax optimal rates for s-Hölder functions in arbitrary dimensions. Improves time series classification with forest proximities.
problem Time series classification accuracy and efficiency.
method PF-GAP, an extension of RF-GAP proximities to proximity forests, combined with Multi-Dimensional Scaling and Local Outlier Factors.
result Forest proximities show stronger connection between misclassified points and outliers.
Interactive graphics help diagnose forest classifiers in R.
problem Exploring and understanding complex ensemble models like random forests.
method Constructing and visualizing data interactively using R packages.
result Interactive graphics provide insights into model complexity and variable importance.
Random forests reduce bias and variance, especially in low SNR settings.
problem Reducing bias and variance in machine learning models, particularly in low SNR scenarios.
method Empirical study of random forests and bagging ensembles, focusing on the importance of mtry tuning. result Random forests reduce both bias and variance, outperforming bagging ensembles in high SNR settings.
New random forest variants achieve optimal performance in high dimensions.
problem Handling dependencies between features in high-dimensional data.
method Using oblique splits in random forests with general split directions.
result Achieved minimax optimal convergence rates in arbitrary dimension.
Model predicts fine dust concentrations in Seoul using LSTM.
problem Predicting concentrations of fine dust in Seoul due to complex interactions.
method Used LSTM based deep learning model to capture non-linear interactions.
result Successfully predicted fine dust concentrations at 25 districts in Seoul.
Study examines survival models for ALS, focusing on proportional hazards assumption.
problem Impact of proportional hazards assumption on survival models for ALS.
method Theoretical and empirical investigation of survival forests and their variants.
result Alternative split procedures can improve model performance in non-proportional hazards situations.
Enhances random forest consistency and introduces DMRF for improved performance.
problem Improving the consistency and efficiency of random forest algorithms.
method Strengthened proof methods and propose DMRF algorithm.
result DMRF achieves better theoretical and experimental performance than previous variants.
Random forests improve probability estimates through kernel regression.
problem Improving the principled approach to random forest probability estimation.
method Forge a connection between random forests and kernel regression, develop a proximity kernel model.
result Improves statistical footing of random forest probability estimation.
Online random forests improve Q-learning performance in specific gym environments.
problem Improving Q-learning performance in reinforcement learning tasks.
method Proposed online random forests as Q-function approximators and growing them as learning progresses.
result Improved performance over state-of-the-art Deep Q-Networks in specific gym environments.
New method learns representations for decision forests using input perturbation.
problem Decision forests struggle with raw structured data and lack effective representations.
method Approximate decision forest gradients through input perturbation.
result Effective representation learning for decision forests without structural changes.
Improved random forest models enhance machine learning predictions.
problem Equal weights for random forest base decision trees are not optimal.
method Proposes algorithms to modify weighting strategy of regular random forest.
result Numerical results show significant improvements over regular random forest.
Proposes a more accurate random forest algorithm by selecting the best-performing trees.
problem Improving accuracy in binary classification problems.
method Best-scored random forest: selects the best-performing tree from random candidates.
result The best-scored random forest can be more accurate than the original random forest.
Local Linear Forests improve random forests for smooth signals and causal inference.
problem Random forests struggle with smooth signals and poor predictive performance in smooth effects.
method Pairing forest kernel with local linear regression adjustment.
result Improves asymptotic rates of convergence and accuracy on real and simulated data.
DDBF improves random forest for imbalanced data.
problem Learning from imbalanced data.
method Incorporates hard example mining into random forest, dynamically removing easy examples.
result DDBF outperforms random forest on multiple datasets.
RPSF improves shapelet-based random forest accuracy and speed.
problem Limitations of random shapelet forest, including high training cost and limited information per node.
method Combines pairs of shapelets, omits threshold searching, and uses DMDI for interpretability.
result Improves accuracy and training speed of shapelet-based random forest.
Optimized DMD for fast atmospheric chemistry forecasting.
problem Forecasting global atmospheric chemistry dynamics efficiently.
method Optimized Dynamic Mode Decomposition (DMD) for reduced order modeling.
result Significant improvement in computational speed and interpretability.
Many scientific and engineering challenges -- ranging from personalized medicine to customized marketing recommendations -- require an understanding of treatment effect heterogeneity. In this paper, we develop a non-parametric causal forest for estimating heterogeneous treatment effects that extends Breiman's widely us…
Decision forests, including Random Forests and Gradient Boosting Trees, have recently demonstrated state-of-the-art performance in a variety of machine learning settings. Decision forests are typically ensembles of axis-aligned decision trees; that is, trees that split only along feature dimensions. In contrast, many r…
A fast method for finding counterfactual explanations for decision forests.
problem Finding counterfactual explanations for decision forests efficiently.
method Constrain optimization to data-populated regions, reducing to nearest-neighbor search.
result Very fast and realistic counterfactual explanations for decision forests.
ggRandomForests package visualizes random forest models for survival data.
problem Analyzing time to event data using random forest methods.
method Unified random forest package for survival analysis with visualizations.
result Demonstrates the strength of random forest methods for prediction and information retrieval in time to event data.
Improves random survival forest model by weighted averaging.
problem Improving the performance of random survival forest.
method Modifies random forest by weighted averaging of trees, optimizing weights via quadratic optimization to maximize Harrell's C-index.
result The weighted random survival forest outperforms the original model in numerical examples.
We improve random forest consistency and performance with DMRF, a new variant.
problem Improving the consistency and performance of random forest models.
method Developed DMRF, a data-driven multinomial random forest, by modifying proof methods and improving data utilization.
result DMRF achieves strong consistency with probability 1, surpassing previous models in classification tasks.