scholarly journals Reducing the Uncertainty of Radiata Pine Site Index Maps Using an Spatial Ensemble of Machine Learning Models

Forests ◽  
2021 ◽  
Vol 12 (1) ◽  
pp. 77
Author(s):  
Gonzalo Gavilán-Acuña ◽  
Guillermo Federico Olmedo ◽  
Pablo Mena-Quijada ◽  
Mario Guevara ◽  
Beatriz Barría-Knopf ◽  
...  
Keyword(s):  
Spatial Scales ◽  
Ensemble Methods ◽  
Radiata Pine ◽  
Site Index ◽  
Parametric Models ◽  
Ensemble Model ◽  
Regression Kriging ◽  
Environmental Surfaces ◽  
Edaphic Variables ◽  
Index Maps

Site Index has been widely used as an age normalised metric in order to account for variation in forest height at a range of spatial scales. Although previous research has used a range of modelling methods to describe the regional variation in Site Index, little research has examined gains that can be achieved through the use of regression kriging or spatial ensemble methods. In this study, an extensive set of environmental surfaces were used as covariates to predict Site Index measurements covering the environmental range of Pinus radiata D. Don plantations in Chile. Using this dataset, the objectives of this research were to (i) compare predictive precision of a range of geostatistical, parametric, and non-parametric models, (ii) determine whether significant gains in precision can be attained through use of regression kriging, (iii) evaluate the precision of a spatial ensemble model that utilises predictions from the five most precise models, through using the model prediction with lowest error for a given pixel, and (iv) produce a map of Site Index across the study area. The five most precise models were all geostatistical and they included ordinary kriging and four regression kriging models that were based on partial least squares or random forests. A spatial ensemble model that was constructed from these five models was the most precise of those developed (RMSE = 1.851 m, RMSE% = 6.38%) and it had relatively little bias. Climatic and edaphic variables were the strongest determinants of Site Index and, in particular, variables that are related to soil water balance were well represented within the most precise predictive models. These results highlight the utility of predicting Site Index using a range of approaches, as these can be used to construct a spatial ensemble that may be more precise than predictions from the constituent models.

scholarly journals Reducing the Uncertainty of Radiata Pine Site Index Maps Using an Spatial Ensemble of Machine Learning Models

2020 ◽  
Author(s):  
Gonzalo Gavilán-Acuña ◽  
Guillermo Federico Olmedo ◽  
Pablo Mena-Quijada ◽  
Mario Guevara ◽  
Beatriz Barria-Knopf ◽  
...  
Keyword(s):  
Spatial Scales ◽  
Ensemble Methods ◽  
Radiata Pine ◽  
Site Index ◽  
Parametric Models ◽  
Ensemble Model ◽  
Regression Kriging ◽  
Environmental Surfaces ◽  
Edaphic Variables ◽  
Index Maps

Site Index has been widely used as an age normalised metric to account for variation in forest height at a range of spatial scales. Although previous research has used a range of modelling methods to describe regional variation in Site Index little research has examined gains that can be achieved through use of regression kriging or spatial ensemble methods. In this study an extensive set of environmental surfaces were used as covariates to predict Site Index measurements covering the environmental range of \textit{Pinus radiata} D. Don plantations in Chile. Using this dataset, the objectives of this research were to (i) compare predictive precision of a range of geostatistical, parametric and non-parametric models, (ii) determine if significant gains in precision can be attained through use of regression kriging, (iii) evaluate the precision of a spatial ensemble model that utilises predictions from the five most precise models, through using the model prediction with lowest error for a given pixel and (iv) produce a map of Site Index across the study area. The five most precise models were all geostatistical and included ordinary kriging and four regression kriging models that were based on partial least squares or random forests. A spatial ensemble model constructed from these five models was the most precise of those developed (RMSE = 1.851 m, RMSE% = 6.38%) and had relatively little bias. Climatic and edaphic variables were the strongest determinants of Site Index and in particular, variables related to soil water balance were well represented within the most precise predictive models. These results highlight the utility of predicting Site Index using a range of approaches, as these can be used to construct a spatial ensemble that may be more precise than predictions from the constituent models.

scholarly journals Creating Landscape-Scale Site Index Maps for the Southeastern US Is Possible with Airborne LiDAR and Landsat Imagery

Forests ◽  
2019 ◽  
Vol 10 (3) ◽  
pp. 234 ◽  
Author(s):  
Ranjith Gopalakrishnan ◽  
Jobriath Kauffman ◽  
Matthew Fagan ◽  
John Coulston ◽  
Valerie Thomas ◽  
...  
Keyword(s):  
Loblolly Pine ◽  
Laser Scanning ◽  
Landsat Imagery ◽  
Site Index ◽  
Airborne Lidar ◽  
Stand Age ◽  
Forest Site ◽  
Large Area ◽  
Southeastern Us ◽  
Index Maps

Sustainable forest management is hugely dependent on high-quality estimates of forest site productivity, but it is challenging to generate productivity maps over large areas. We present a method for generating site index (a measure of such forest productivity) maps for plantation loblolly pine (Pinus taeda L.) forests over large areas in the southeastern United States by combining airborne laser scanning (ALS) data from disparate acquisitions and Landsat-based estimates of forest age. For predicting canopy heights, a linear regression model was developed using ALS data and field measurements from the Forest Inventory and Analysis (FIA) program of the US Forest Service (n = 211 plots). The model was strong (R2 = 0.84, RMSE = 1.85 m), and applicable over a large area (~208,000 sq. km). To estimate the site index, we combined the ALS estimated heights with Landsat-derived maps of stand age and planted pine area. The estimated bias was low (−0.28 m) and the RMSE (3.8 m, relative RMSE: 19.7%, base age 25 years) was consistent with other similar approaches. Due to Landsat-related constraints, our methodology is valid only for relatively young pine plantations established after 1984. We generated 30 m resolution site index maps over a large area (~832 sq. km). The site index distribution had a median value of 19.4 m, the 5th percentile value of 13.0 m and the 95th percentile value of 23.3 m. Further, using a watershed level analysis, we ranked these regions by their estimated productivity. These results demonstrate the potential and value of remote sensing based large-area site index maps.

Quantification of realised genetic gain in radiata pine and its incorporation into growth and yield modelling systems

2015 ◽  
Vol 45 (12) ◽  
pp. 1676-1687 ◽  
Author(s):  
Mark O. Kimberley ◽  
John R. Moore ◽  
Heidi S. Dungey
Keyword(s):  
New Zealand ◽  
Genetic Gain ◽  
Genetic Improvement ◽  
Volume Growth ◽  
Radiata Pine ◽  
Site Index ◽  
Growth And Yield ◽  
Wide Range ◽  
Unit Increase ◽  
Using Data

Realised genetic gain for radiata pine (Pinus radiata D. Don) was estimated using data from 46 installations of three series of block-plot trials spanning a wide range of site types throughout New Zealand. These trials contained 63 unique seedlots with different levels of genetic improvement. Realised genetic gain was quantified using two measures of productivity: site index and 300 Index (a measure of volume productivity). The level of genetic improvement of each seedlot was determined by its GF Plus rating, a genetic rating system based on breeding values used for New Zealand radiata pine. There was a positive relationship between GF Plus rating and both productivity measures. Differences of 25% in total standing volume at age 30 years and of 5.6% in site index were found between unimproved (GF Plus 9.9) and highly improved (GF Plus 25) seedlots. Each unit increase in GF Plus rating was associated with a 1.51% increase in volume growth rate. In absolute terms, the magnitude of the increase was greater on more productive sites compared with less productive sites, although in percentage terms, it varied little between sites or regions. Quantification of genetic gain in this manner enables it to be easily incorporated into existing growth and yield simulators.

Trembling aspen site index in relation to environmental measures of site quality at two spatial scales

2002 ◽  
Vol 32 (1) ◽  
pp. 112-119 ◽  
Author(s):  
Han YH Chen ◽  
Pavel V Krestov ◽  
Karel Klinka
Keyword(s):  
Populus Tremuloides ◽  
Factor Model ◽  
Spatial Scales ◽  
Site Index ◽  
Site Quality ◽  
Slope Aspect ◽  
Moisture Regime ◽  
Trembling Aspen ◽  
Geographic Scale ◽  
Environmental Measures

To evaluate the variation in trembling aspen (Populus tremuloides Michx.) productivity at a large geographic scale, we examined the relationships between site index and environmental factors from 142 even-aged, fully stocked stands located on a variety of sites across interior British Columbia. Site index was derived from stem analysis and the environmental measures included climate surrogates (latitude, longitude, and elevation), biogeoclimatic zone, slope– aspect, actual soil moisture regime (SMR), and soil nutrient regime (SNR). The spatial gradients (latitude, longitude, and elevation), slope–aspect, SMR, and SNR affected aspen site index, but their relationships greatly varied with biogeoclimatic zone. At the provincial scale, these relationships were weaker than on the zonal scale. Among the models developed for predicting aspen site index, we recommend the zone-specific all-factor model for application, which explained 82% of the variation of site index and provided unbiased and precise predictions.

A Novel Ensemble Model - The Random Granular Reflections

2021 ◽  
Vol 179 (2) ◽  
pp. 183-203
Author(s):  
Piotr Artiemjew ◽  
Krzysztof Ropiak
Keyword(s):  
Random Forests ◽  
Learning Process ◽  
Ensemble Methods ◽  
Training System ◽  
New Method ◽  
Ensemble Model ◽  
Optimal Parameters ◽  
New Approach ◽  
Decision Systems

One of the most popular families of techniques to boost classification are Ensemble methods. Random Forests, Bagging and Boosting are the most popular and widely used ones. This article presents a novel Ensemble Model, named Random Granular Reflections. The algorithm used in this new approach creates an ensemble of homogeneous granular decision systems. The first step of the learning process is to take the training system and cover it with random homogeneous granules (groups of objects from the same decision class that are as little indiscernible from each other as possible). Next, granular reflection is created, which is finally used in the classification process. Results obtained by our initial experiments show that this approach is promising and comparable with other tested methods. The main advantage of our new method is that it is not necessary to search for optimal parameters while looking for granular reflections in the subsequent iterations of our ensemble model.

scholarly journals A Bi-LSTM Based Ensemble Algorithm for Prediction of Protein Secondary Structure

2019 ◽  
Vol 9 (17) ◽  
pp. 3538 ◽  
Author(s):  
Hailong Hu ◽  
Zhong Li ◽  
Arne Elofsson ◽  
Shangxin Xie
Keyword(s):  
Secondary Structure ◽  
Cross Validation ◽  
State Of The Art ◽  
Protein Secondary Structure ◽  
Ensemble Methods ◽  
Ensemble Model ◽  
Training Process ◽  
Independent Test ◽  
Test Sets ◽  
Fold Cross Validation

The prediction of protein secondary structure continues to be an active area of research in bioinformatics. In this paper, a Bi-LSTM based ensemble model is developed for the prediction of protein secondary structure. The ensemble model with dual loss function consists of five sub-models, which are finally joined by a Bi-LSTM layer. In contrast to existing ensemble methods, which generally train each sub-model and then join them as a whole, this ensemble model and sub-models can be trained simultaneously and the performance of each model can be observed and compared during the training process. Three independent test sets (e.g., data1199, 513 protein Cuff & Barton set (CB513) and 203 proteins from Critical Appraisals Skills Programme (CASP203)) are employed to test the method. On average, the ensemble model achieved 84.3% in Q 3 accuracy and 81.9% in segment overlap measure ( SOV ) score by using 10-fold cross validation. There is an improvement of up to 1% over some state-of-the-art prediction methods of protein secondary structure.

scholarly journals A Spatial Forestry Productivity Potential Model for Pinus arizonica Engelm, a Key Timber Species from Northwest Mexico

2019 ◽  
Vol 11 (3) ◽  
pp. 829 ◽  
Author(s):  
Martin Martínez-Salvador ◽  
Ricardo Mata-Gonzalez ◽  
Alfredo Pinedo-Alvarez ◽  
Carlos R. Morales-Nieto ◽  
Jesús A. Prieto-Amparán ◽  
...  
Keyword(s):  
Climate Change ◽  
Potential Model ◽  
Site Index ◽  
Similar Species ◽  
Timber Species ◽  
Northwest Mexico ◽  
Productive Potential ◽  
Si Model ◽  
Edaphic Variables ◽  
Productivity Potential

Pinus arizonica is a widely distributed tree species growing in temperate forests of Northwest Mexico where it is utilized through different regeneration harvest methods. Yet, management models based on estimations of its productive potential are sorely lacking. In this study, a procedure to create a productive map using site index (SI) equations and Geographic Information Systems (GIS) was developed. A SI model for P. arizonica was created for the study area and used to classify a group of randomly sampled plots on three productivity categories (High, Medium, and Low) for management purposes. Climatic, topographic and edaphic variables were determined on the sampled plots. Then, a statistically-based analysis was performed to identify the climatic, topographic and edaphic variables significantly influencing the productivity levels. Based on the values of these significant variables, a map of productive potential was elaborated for the whole study area. Sites with the highest productivity were those with slopes ≤12°, soil depths ≥0.46 m, minimum and maximum mean annual temperatures of 5 °C and 18 °C respectively, and precipitation ≥900 mm. This methodology could be considered for similar species/conditions where productivity models do not exist or to update old models rendered obsolete by climate change.

Sign in / Sign up

Export Citation Format

Share Document