Article
Engineering, Aerospace
Ulas Yunus Ozkan, Tufan Demirel, Ibrahim Ozdemir, Serhun Saglam, Ahmet Mert
Summary: This study examined the capability of combined LiDAR/WorldView-3 data in estimating plot-level stand attributes in a complex forest in northwest Turkey. Prediction models were developed at different levels, with multiple linear regression (MLR) and random forest (RF) modeling approaches tested. The results showed higher prediction accuracy for height at tree species level and forest types level, with homogeneous coniferous stands providing higher estimation accuracy. The combination of aerial laser scanning and high resolution satellite data has potential for predicting stand attributes in complex forest ecosystems.
ADVANCES IN SPACE RESEARCH
(2022)
Article
Engineering, Electrical & Electronic
Mengmeng Li, Yi Liu, Qibin Zheng, Gengsong Li, Wei Qin
Summary: This paper introduces a novel data imputation algorithm, PSOHM, which utilizes particle swarm optimization to impute both continuous and discrete features in high-dimensional mixed missing variables data. The algorithm outperforms traditional methods in terms of classification performance on various datasets.
ELECTRONICS LETTERS
(2023)
Article
Computer Science, Information Systems
Barbara Zogala-Siudem, Szymon Jaroszewicz
Summary: The approach efficiently constructs stepwise regression models in a very high dimensional setting using a multidimensional index, automatically selecting predictors and yielding results identical to standard stepwise regression but significantly faster. Tested on a large statistical database, it has been shown to produce interpretable and accurate models superior to other approaches for modeling with ultrahigh dimensional data.
INFORMATION SCIENCES
(2021)
Article
Engineering, Aerospace
Mohamed Musthafa, Gulab Singh
Summary: This study utilizes GEDI LiDAR data and field-measured biomass to develop a method for estimating forest aboveground biomass (AGB) and develops an AGB model. The results demonstrate the potential of using GEDI LiDAR data to improve the accuracy of forest AGB modeling.
ADVANCES IN SPACE RESEARCH
(2022)
Article
Environmental Studies
Kai Moriguchi
Summary: A method was developed in this study to determine the optimal selection of subsidized forest stands, with the goal of maximizing the efficient use of public funds. By numerically determining the minimum subsidy and optimal forest harvesting schedule, and using a simple sorting method to identify the best selection of subsidized forest stands, the study aims to minimize annual government expenditure under normal forest conditions.
Article
Environmental Sciences
Rorai Pereira Martins-Neto, Antonio Maria Garcia Tommaselli, Nilton Nobuhiro Imai, Hassan Camil David, Milto Miltiadou, Eija Honkavaara
Summary: This study investigated the estimation of stand and diversity variables in disturbed tropical forests using LiDAR data and machine learning techniques. By testing different transformations of LiDAR metrics and various machine learning methods, the study identified the best approach for estimating forest variables accurately in heterogeneous forests.
Article
Biodiversity Conservation
Samuel P. Reed, Alejandro A. Royo, Alexander T. Fotis, Kathleen S. Knight, Charles E. Flower, Peter S. Curtis
Summary: High browsing pressure from white-tailed deer during stand initiation can have a long-term impact on stand and canopy structure, leading to lower species diversity and tree density, resulting in taller and less dense canopies. Considering the legacy of ungulate herbivory on canopy structure may inform both land management and our understanding of ecological function.
JOURNAL OF APPLIED ECOLOGY
(2022)
Article
Computer Science, Interdisciplinary Applications
Leyre Torre-Tojal, Aitor Bastarrika, Ana Boyano, Jose Manuel Lopez-Guede, Manuel Grana
Summary: This article utilizes random forest models to estimate the biomass of Pinus radiata species in a region of the Basque Autonomous Community. By tuning the hyperparameters and conducting cross-validation, two models with high R-2 values were obtained. These models were then applied to the municipality of Orozko, predicting a biomass that is 16-18% higher than the predictions made by the Basque Government.
JOURNAL OF COMPUTATIONAL SCIENCE
(2022)
Article
Green & Sustainable Science & Technology
Giulia Del Serrone, Laura Moretti
Summary: This study investigates the environmental performances of clinker production and the factors driving emissions. Through assessing 41 different grey clinkers produced in Italy from 2016 to 2021, it identifies pet coke, fossil fuels, natural raw materials, and lorry transport as the most significant variables. The findings provide important guidance for cement producers to develop low-impacting clinker recipes.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Environmental Sciences
Junpeng Zhao, Lei Zhao, Erxue Chen, Zengyuan Li, Kunpeng Xu, Xiangyuan Ding
Summary: Forest canopy height is an important parameter for estimating forest aboveground biomass, growing stock volume, and carbon storage. In this study, a new estimation framework named RK-GHMB was developed to quantify the uncertainty of the estimation result. The result shows that RK-GHMB can achieve a high accuracy in estimating forest canopy height and can be used for monitoring purposes.
Article
Computer Science, Interdisciplinary Applications
Hakan Ezgi Kiziloz, Ayca Deniz
Summary: In this study, a robust framework for feature selection is built leveraging the multi-core nature of a regular PC. Multiple execution settings are facilitated through the use of two multiobjective selection algorithms, four initial population generation methods, and five machine learning techniques. Extensive experiments on 11 UCI benchmark datasets show remarkable improvement in terms of maximum accuracy.
COMPUTERS & INDUSTRIAL ENGINEERING
(2021)
Article
Automation & Control Systems
Sergii Voronov, Voronov Daniel Jung, Erik Frisk
Summary: The paper introduces a forest-based variable selection algorithm, named Variable Depth Distribution, to measure the importance of variables. The algorithm is developed for datasets with correlated variables and can identify important variables in different applications.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2021)
Article
Geography, Physical
Karun R. Dayal, Sylvie Durrieu, Kamel Lahssini, Samuel Alleaume, Marc Bouvier, Jean-Matthieu Monnet, Jean-Pierre Renaud, Frederic Reverse
Summary: This study aims to investigate the influence of lidar scan angle on ABA predictions and evaluate the potential of voxelisation approaches in mitigating scan angle effects. The results showed that models built with point clouds scanned from multiple flight lines were more robust, while datasets with a predominantly nadir configuration did not always lead to better predictions. The use of voxelisation methods helped to mitigate the impacts of changes in scan angles.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Environmental Sciences
Ma Angeles Varo-Martinez, Rafael M. Navarro-Cerrillo
Summary: This study explored the potential of integrating multispectral WorldView-2 and Airborne Laser Scanning data for stand delineation in Pinus sylvestris plantations. By quantifying needle pigments and leaf area index, and using vegetation indices and ALS-derived metrics, the study successfully estimated and mapped tree crown variables. The results underscored the potential of WV-2 and ALS data integration for assessing stand delineation based on tree health status.
Letter
Computer Science, Information Systems
Baoying Ma, Li Wan, Nianmin Yao, Shuping Fan, Yan Zhang
Summary: This research proposes a method to improve fault detection rate by selecting test cases using genetic algorithm to achieve both path coverage and coverage balance. Experimental results demonstrate that this method can efficiently select test cases that meet testing requirements.
FRONTIERS OF COMPUTER SCIENCE
(2021)
Review
Computer Science, Artificial Intelligence
Pedro Lara-Benitez, Manuel Carranza-Garcia, Jose C. Riquelme
Summary: Research demonstrates that long short-term memory (LSTM) and convolutional networks (CNN) are the best options for time series forecasting, with LSTMs yielding the most accurate predictions; CNNs show more stable performance under different parameter configurations and are also more efficient.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2021)
Article
Forestry
Albert Castillo-Lopez, Geronimo Quinonez-Barraza, Ulises Dieguez-Aranda, Jose Javier Corral-Rivas
Summary: Estimating tree volume components using compatible taper and merchantable volume systems based on volume ratio models showed over 97% explained variability for four pine species. This method proves to be a simple and consistent alternative for estimating tree volume components in forests with uneven-age and mixed-species stands in Oaxaca, Mexico.
Article
Environmental Sciences
Manuel Carranza-Garcia, Jesus Torres-Mateo, Pedro Lara-Benitez, Jorge Garcia-Gutierrez
Summary: In this study, the performance of existing 2D detection systems for self-driving vehicles on a multi-class problem was evaluated and compared in different scenarios. Despite the increasing popularity of one-stage detectors, it was found that two-stage detectors still provide the most robust performance.
Article
Forestry
Miguel Angel Gonzalez-Rodriguez, Ulises Dieguez-Aranda
Summary: Parametric indirect models derived from stem analysis of dominant trees were found to be more robust for predicting Site Index of Scots pine stands in relation to climate, compared to rule-based machine learning techniques.
ANNALS OF FOREST SCIENCE
(2021)
Article
Biodiversity Conservation
M. A. Gonzalez-Rodriguez, U. Dieguez-Aranda
Summary: This study proposed a method for delimiting the uncertainty of climate-sensitive extrapolations of forest productivity, using Support Vector Regression to predict forest productivity in Galicia. The analysis revealed that extrapolations for unseen climatic conditions were extremely regularised, leading to narrow validity areas for the model.
ECOLOGICAL INDICATORS
(2021)
Article
Computer Science, Artificial Intelligence
Manuel Carranza-Garcia, Pedro Lara-Benitez, Jorge Garcia-Gutierrez, Jose C. Riquelme
Summary: This study presents an enhanced 2D object detector based on Faster R-CNN specifically designed for autonomous vehicles. By improving anchor generation and addressing performance drop in minority classes, the proposed perspective-aware methodology and spatial information enhancement module significantly increased detection accuracy. Utilizing ensemble models led to a further 9.69% mAP improvement in accuracy.
Article
Environmental Sciences
Cecilia Alonso-Rego, Stefano Arellano-Perez, Juan Guerra-Hernandez, Juan Alberto Molina-Valero, Adela Martinez-Calvo, Cesar Perez-Cruzado, Fernando Castedo-Dorado, Eduardo Gonzalez-Ferreiro, Juan Gabriel alvarez-Gonzalez, Ana Daria Ruiz-Gonzalez
Summary: This study utilized low-density ALS and TLS metrics data, combined with machine learning techniques, to provide a promising alternative for accurately estimating variables related to surface and canopy fires on a large scale. The combination of ALS and TLS metrics improved the accuracy of estimates for various variables, showing potential in replacing traditional field inventories for obtaining valuable information about surface and canopy fuel variables.
Article
Economics
Jose Mario Gonzalez-Gonzalez, Miguel Ernesto Vazquez-Mendez, Ulises Dieguez-Aranda
Summary: This study introduces several multi-objective models for forest harvest scheduling in forests with single-species, even-aged stands using a continuous formulation. By designing new metrics for continuous decision variables, the study avoids simulation of alternative management prescriptions before the optimization process and proves the robustness of the continuous formulation in forests with different structures. The proposed approach shows significant advantages in terms of computational time efficiency over the commonly used evolutionary algorithm.
FOREST POLICY AND ECONOMICS
(2022)
Article
Computer Science, Artificial Intelligence
Manuel Carranza-Garcia, F. Javier Galan-Sales, Jose Maria Luna-Romera, Jose C. Riquelme
Summary: This paper proposes a novel data fusion architecture for object detection in autonomous driving, using camera and LiDAR data to achieve reliable performance. With deep learning models and sensor data, our approach significantly outperforms previous methods in various weather and lighting conditions.
INTEGRATED COMPUTER-AIDED ENGINEERING
(2022)
Article
Mathematics, Applied
Pedro Lara-Benitez, Manuel Carranza-Garcia, David Gutierrez-Aviles, Jose C. Riquelme
Summary: This study aims to evaluate the performance of different types of deep learning architectures for data streaming classification. The results indicate that convolutional architectures achieve higher accuracy and efficiency but are also most sensitive to concept drifts.
LOGIC JOURNAL OF THE IGPL
(2023)
Article
Chemistry, Multidisciplinary
Laura Madrid-Marquez, Cristina Rubio-Escudero, Beatriz Pontes, Antonio Gonzalez-Perez, Jose C. Riquelme, Maria E. Saez
Summary: This study introduces a new software tool called MOMIC, which provides a complete analysis environment for analyzing and integrating multi-omics data on a single, easy-to-use platform. It offers high editability, reproducibility, and is of great importance for deriving meaningful biological knowledge.
APPLIED SCIENCES-BASEL
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Tomas Cabello-Lopez, Manuel Canizares-Juan, Manuel Carranza-Garcia, Jorge Garcia-Gutierrez, Jose C. Riquelme
Summary: This study analyzed wind energy generation data from the Spanish power grid and evaluated the improvement in forecasting quality by detecting concept drifts and retraining models. The experimental results showed that the concept drift approach significantly improved the accuracy of forecasting.
HYBRID ARTIFICIAL INTELLIGENT SYSTEMS, HAIS 2022
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Manuel Carranza-Garcia, Pedro Lara-Benitez, Jose Maria Luna-Romera, Jose C. Riquelme
Summary: The importance of feature selection for forecasting solar irradiance time series using spatio-temporal data is studied, and it is found that proper feature selection significantly enhances the forecasting accuracy.
16TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING MODELS IN INDUSTRIAL AND ENVIRONMENTAL APPLICATIONS (SOCO 2021)
(2022)
