scholarly journals Forest tree species distribution for Europe 2000-2020: mapping potential and realized distributions using spatiotemporal Machine Learning

2022 ◽  
Author(s):  
Carmelo Bonannella ◽  
Tomislav Hengl ◽  
Johannes Heisig ◽  
Leandro Parente ◽  
Marvin N Wright ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
High Resolution ◽  
Potential Distribution ◽  
Forest Tree ◽  
Quercus Suber ◽  
Ensemble Model ◽  
Individual Model ◽  
Salix Caprea ◽  
Distribution Maps

Abstract Paper describes a data-driven framework based on spatio-temporal ensemble machine learning to produce distribution maps for 16 forest tree species (Abies alba Mill., Castanea sativa Mill. , Corylus avellana L., Fagus sylvatica L., Olea europaea L., Picea abies L. H. Karst., Pinus halepensis Mill., Pinus nigra J. F. Arnold, Pinus pinea L., Pinus sylvestris L., Prunus avium L., Quercus cerris L., Quercus ilex L., Quercus robur L., Quercus suber L. and Salix caprea L.) at high spatial resolution (30 m). Tree occurrence data for a total of 3 million of points was used to train different Machine Learning (ML) algorithms: random forest, gradient-boosted trees, generalized linear models, k-nearest neighbors, CART and an artificial neural network. A stack of 585 coarse and high resolution covariates representing spectral reflectance (Landsat bands, spectral indices; time-series of seasonal composites), different biophysical conditions (i.e. temperature, precipitation, elevation, lithology) and biotic competition (other species distribution maps) was used as predictors for realized distributions, while potential distribution was modelled with environmental predictors only. Logloss and computing time were used to select the three best algorithms to train an ensemble model based on stacking with a logistic regressor as a meta-learner for each species. High resolution (30 m) probability and model uncertainty maps of realized distribution were produced for each species using a time window of 4 years for a total of 6 distribution maps per species for the studied period, while for potential distributions only one map per species was produced. Results of spatial cross validation show that Olea europaea and Quercus suber achieved the best performances in both potential and realized distribution, while Pinus sylvestris and Salix caprea achieved the worst. Further analysis shows that fine-resolution models consistently outperformed coarse resolution models (250 m) for realized distribution (average decrease in logloss: +53%). Realized distribution models achieved higher predictive performances than potential distribution ones. Importance of predictor variables differed across species and models, with the green band for summer and the NDWI and NDVI for fall for realized distribution and the diffuse irradiation and precipitation of the driest quarter being the most important and frequent for potential distribution. The ensemble model outperformed or performed as good as the best individual model in all potential species distributions, while for ten species it performed worse than the best individual model in modeling realized distributions. The framework shows how combining continuous and consistent EO time series data with state of the art ML can be used to derive dynamic distribution maps. The produced time-series occurrence predictions can be used to quantify temporal trends and detect potential forest degradation.

scholarly journals Machine Learning Paradigm towards Content Based Image Retrieval on High Resolution Satellite Images

2019 ◽  
Vol 9 (2S2) ◽  
pp. 999-1005
Keyword(s):  
Machine Learning ◽  
High Resolution ◽  
Image Retrieval ◽  
Satellite Images ◽  
Satellite Image ◽  
Content Based Image Retrieval ◽  
Support Vector ◽  
Ensemble Model ◽  
Learning Paradigm ◽  
High Resolution Satellite Images

In the current era, content based image retrieval based on pattern recognition and classification using machine learning paradigm is an innovative way. In order to retrieve high resolution satellite images Support Vector Machine (SVM) a machine learning paradigm is helpful for learning process and for pattern recognition and classification; ensemble methods give better machine learning results. In this paper, SVM based on random subspace and boosting ensemble learning is proposed for very high resolution satellite image retrieval. The learned SVM ensemble model is used to identify the images that most similar informative for active learning. A bias-weighting system is developed to direct the ensemble model to pay more attention on the positive examples than the negative ones. The UCMerced land use satellite image dataset is used for experimental work. Accuracy and error rate are found to be precise. The tentative effects illustrate that the proposed model derived enhanced retrieval accurateness at the optimum level as well as significantly more effective than existing approaches. The proposed method can diminish the gap dimensionality and conquer the difficulty. The comparisons are evaluated by using precision and recall measurements. Comparative analysis observed that the retrieval time for a particular image have been reduced and the precision is increased. The primary aim of this paper is to represent the significance of ensemble learning with support vector machine in efficient retrieval of image.

scholarly journals A High-Resolution Spatial and Time-Series Labeled Unmanned Aerial Vehicle Image Dataset for Middle-Season Rice

2020 ◽  
Vol 9 (12) ◽  
pp. 728
Author(s):  
Dongbo Zhou ◽  
Shuangjian Liu ◽  
Jie Yu ◽  
Hao Li
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Deep Learning ◽  
High Resolution ◽  
Unmanned Aerial Vehicle ◽  
Temporal Information ◽  
Learning Networks ◽  
Image Dataset ◽  
Aerial Vehicle ◽  
Uav Image

The existing remote sensing image datasets target the identification of objects, features, or man-made targets but lack the ability to provide the date and spatial information for the same feature in the time-series images. The spatial and temporal information is important for machine learning methods so that networks can be trained to support precision classification, particularly for agricultural applications of specific crops with distinct phenological growth stages. In this paper, we built a high-resolution unmanned aerial vehicle (UAV) image dataset for middle-season rice. We scheduled the UAV data acquisition in five villages of Hubei Province for three years, including 11 or 13 growing stages in each year that were accompanied by the annual agricultural surveying business. We investigated the accuracy of the vector maps for each field block and the precise information regarding the crops in the field by surveying each village and periodically arranging the UAV flight tasks on a weekly basis during the phenological stages. Subsequently, we developed a method to generate the samples automatically. Finally, we built a high-resolution UAV image dataset, including over 500,000 samples with the location and phenological growth stage information, and employed the imagery dataset in several machine learning algorithms for classification. We performed two exams to test our dataset. First, we used four classical deep learning networks for the fine classification of spatial and temporal information. Second, we used typical models to test the land cover on our dataset and compared this with the UCMerced Land Use Dataset and RSSCN7 Dataset. The results showed that the proposed image dataset supported typical deep learning networks in the classification task to identify the location and time of middle-season rice and achieved high accuracy with the public image dataset.

scholarly journals High-Resolution Gridded Livestock Projection for Western China Based on Machine Learning

2021 ◽  
Vol 13 (24) ◽  
pp. 5038
Author(s):  
Xianghua Li ◽  
Jinliang Hou ◽  
Chunlin Huang
Keyword(s):  
Machine Learning ◽  
High Resolution ◽  
Western China ◽  
Support Vector ◽  
Distribution Data ◽  
Learning Models ◽  
Distribution Maps ◽  
Livestock Density ◽  
Machine Learning Models ◽  
Cattle And Sheep

Accurate high-resolution gridded livestock distribution data are of great significance for the rational utilization of grassland resources, environmental impact assessment, and the sustainable development of animal husbandry. Traditional livestock distribution data are collected at the administrative unit level, which does not provide a sufficiently detailed geographical description of livestock distribution. In this study, we proposed a scheme by integrating high-resolution gridded geographic data and livestock statistics through machine learning regression models to spatially disaggregate the livestock statistics data into 1 km × 1 km spatial resolution. Three machine learning models, including support vector machine (SVM), random forest (RF), and deep neural network (DNN), were constructed to represent the complex nonlinear relationship between various environmental factors (e.g., land use practice, topography, climate, and socioeconomic factors) and livestock density. By applying the proposed method, we generated a set of 1 km × 1 km spatial distribution maps of cattle and sheep for western China from 2000 to 2015 at five-year intervals. Our projected cattle and sheep distribution maps reveal the spatial heterogeneity structures and change trend of livestock distribution at the grid level from 2000 to 2015. Compared with the traditional census livestock density, the gridded livestock distribution based on DNN has the highest accuracy, with the determinant coefficient (R2) of 0.75, root mean square error (RMSE) of 9.82 heads/km2 for cattle, and the R2 of 0.73, RMSE of 31.38 heads/km2 for sheep. The accuracy of the RF is slightly lower than the DNN but higher than the SVM. The projection accuracy of the three machine learning models is superior to those of the published Gridded Livestock of the World (GLW) datasets. Consequently, deep learning has the potential to be an effective tool for high-resolution gridded livestock projection by combining geographic and census data.

Sign in / Sign up

Export Citation Format

Share Document