scholarly journals Comparison of GF2 and SPOT6 Imagery on Canopy Cover Estimating in Northern Subtropics Forest in China

Forests ◽  
2020 ◽  
Vol 11 (4) ◽  
pp. 407
Author(s):  
Jingjing Zhou ◽  
Yuanyong Dian ◽  
Xiong Wang ◽  
Chonghuai Yao ◽  
Yongfeng Jian ◽  
...  
Keyword(s):  
Ensemble Learning ◽  
Spatial Resolution ◽  
Forest Canopy ◽  
High Spatial Resolution ◽  
Mixed Forest ◽  
Canopy Cover ◽  
Learning Model ◽  
Gradient Boosting ◽  
Learning Models ◽  
Adaptive Boosting

Canopy cover is an important vegetation attribute used for many environmental applications such as defining management objectives, thinning and ecological modeling. However, the estimation of canopy cover from high spatial resolution imagery is still a difficult task due to limited spectral information and the heterogeneous pixel values of the same canopy. In this paper, we compared the capacity of two high spatial resolution sensors (SPOT6 and GF2) using three ensemble learning models (Adaptive Boosting (AdaBoost), Gradient Boosting (GDBoost), and random forest (RF)), to estimate canopy cover (CC) in a Chinese northern subtropics forest. Canopy cover across 97 plots was measured across 41 needle forest plots, 24 broadleaf forest plots, and 32 mixed forest plots. Results showed that (1) the textural features performed more importantly than spectral variables according to the number of variables in the top ten predictors in estimating canopy cover (CC) in both SPOT6 and GF2. Moreover, the vegetation indices in spectral variables had a lower relative importance value than the band reflectance variables. (2) GF2 imagery outperformed SPOT6 imagery in estimating CC when using the ensemble learning model in our data. On average across the models, the R2 was almost 0.08 higher for GF2 over SPOT6. Likewise, the average RMSE and average MAE were 0.002 and 0.01 lower in GF2 than in SPOT6. (3) The ensemble learning model showed good results in estimating CC, yet the different models performed a little differently in the results. Additionally, the GDBoost model performed the best of all the ensemble learning models with R2 = 0.92, root mean square error (RMSE) = 0.001 and mean absolute error (MAE) = 0.022.

scholarly journals A Comparative Analysis of Novel Deep Learning Models and Ensemble Learning Models to Predict the Allergenicity of Food Allergens

2021 ◽  
Author(s):  
Liyang Wang ◽  
Dantong Niu ◽  
Xinjie Zhao ◽  
Xiaoya Wang ◽  
Mengzhen Hao ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Ensemble Learning ◽  
Food Allergen ◽  
Learning Model ◽  
Gradient Boosting ◽  
Food Allergens ◽  
Learning Models ◽  
Allergen Identification ◽  
Machine Learning Models

AbstractTraditional food allergen identification mainly relies on in vivo and in vitro experiments, which often needs a long period and high cost. The artificial intelligence (AI)-driven rapid food allergen identification method has solved the two drawbacks and is becoming an efficient auxiliary tool. Aiming to overcome the limitations of lower accuracy of traditional machine learning models in predicting the allergenicity of food allergens, this work proposed to introduce transformer deep learning model with self-attention mechanism and ensemble learning model (representative as Light Gradient Boosting Machine (LightGBM) and eXtreme Gradient Boosting (XGBoost)) to solve the problem. In order to highlight the superiority of the proposed novel method, the study also selected various commonly used machine learning models as the baseline classifiers. The results of 5-fold cross-validation found that the AUC of the deep model was the highest (0.9400), which was better than the ensemble learning and baseline algorithms. But it needed to be pre-trained, and the training cost was highest. By comparing the characteristics of transformer model and boosting models, it can be analyzed that the two types of models have their own advantages, which provides novel clues and inspiration for the rapid prediction of food allergens in the future.

scholarly journals Detecting Long-Term Urban Forest Cover Change and Impacts of Natural Disasters Using High-Resolution Aerial Images and LiDAR Data

2020 ◽  
Vol 12 (11) ◽  
pp. 1820
Author(s):  
Raoul Blackman ◽  
Fei Yuan
Keyword(s):  
Remote Sensing ◽  
Ecosystem Services ◽  
Forest Canopy ◽  
High Spatial Resolution ◽  
Urban Forest ◽  
Urban Canopy ◽  
Canopy Cover ◽  
Random Point ◽  
Aerial Images ◽  
Lidar Data

Urban forests provide ecosystem services; tree canopy cover is the basic quantification of ecosystem services. Ground assessment of the urban forest is limited; with continued refinement, remote sensing can become an essential tool for analyzing the urban forest. This study addresses three research questions that are essential for urban forest management using remote sensing: (1) Can object-based image analysis (OBIA) and non-image classification methods (such as random point-based evaluation) accurately determine urban canopy coverage using high-spatial-resolution aerial images? (2) Is it possible to assess the impact of natural disturbances in addition to other factors (such as urban development) on urban canopy changes in the classification map created by OBIA? (3) How can we use Light Detection and Ranging (LiDAR) data and technology to extract urban canopy metrics accurately and effectively? The urban forest canopy area and location within the City of St Peter, Minnesota (MN) boundary between 1938 and 2019 were defined using both OBIA and random-point-based methods with high-spatial-resolution aerial images. Impacts of natural disasters, such as the 1998 tornado and tree diseases, on the urban canopy cover area, were examined. Finally, LiDAR data was used to determine the height, density, crown area, diameter, and volume of the urban forest canopy. Both OBIA and random-point methods gave accurate results of canopy coverages. The OBIA is relatively more time-consuming and requires specialist knowledge, whereas the random-point-based method only shows the total coverage of the classes without locational information. Canopy change caused by tornado was discernible in the canopy OBIA-based classification maps while the change due to diseases was undetectable. To accurately exact urban canopy metrics besides tree locations, dense LiDAR point cloud data collected at the leaf-on season as well as algorithms or software developed specifically for urban forest analysis using LiDAR data are needed.

scholarly journals Mapping the Mangrove Forest Canopy Using Spectral Unmixing of Very High Spatial Resolution Satellite Images

2019 ◽  
Vol 11 (3) ◽  
pp. 367 ◽  
Author(s):  
Florent Taureau ◽  
Marc Robin ◽  
Christophe Proisy ◽  
François Fromard ◽  
Daniel Imbert ◽  
...  
Keyword(s):  
Spatial Resolution ◽  
Forest Structure ◽  
Mangrove Forest ◽  
Satellite Images ◽  
Forest Canopy ◽  
High Spatial Resolution ◽  
Spectral Unmixing ◽  
Very High Spatial Resolution ◽  
Very High ◽  
Mangrove Structure

Despite the low tree diversity and scarcity of the understory vegetation, the high morphological plasticity of mangrove trees induces, at the stand level, a very large variability of forest structures that need to be mapped for assessing the functioning of such complex ecosystems. Fully constrained linear spectral unmixing (FCLSU) of very high spatial resolution (VHSR) multispectral images was tested to fine-scale map mangrove zonations in terms of horizontal variation of forest structure. The study was carried out on three Pleiades-1A satellite images covering French island territories located in the Atlantic, Indian, and Pacific Oceans, namely Guadeloupe, Mayotte, and New Caledonia archipelagos. In each image, FCLSU was trained from the delineation of areas exclusively related to four components including either pure vegetation, soil (ferns included), water, or shadows. It was then applied to the whole mangrove cover imaged for each island and yielded the respective contributions of those four components for each image pixel. On the forest stand scale, the results interestingly indicated a close correlation between FCLSU-derived vegetation fractions and canopy closure estimated from hemispherical photographs (R2 = 0.95) and a weak relation with the Normalized Difference Vegetation Index (R2 = 0.29). Classification of these fractions also offered the opportunity to detect and map horizontal patterns of mangrove structure in a given site. K-means classifications of fraction indeed showed a global view of mangrove structure organization in the three sites, complementary to the outputs obtained from spectral data analysis. Our findings suggest that the pixel intensity decomposition applied to VHSR multispectral satellite images can be a simple but valuable approach for (i) mangrove canopy monitoring and (ii) mangrove forest structure analysis in the perspective of assessing mangrove dynamics and productivity. As with Lidar-based surveys, these potential new mapping capabilities deserve further physically based interpretation of sunlight scattering mechanisms within forest canopy.

scholarly journals Pattern recognition of forest canopy using the airborne hyperspectral data and multi-bands high spatial resolution satellite sensor worldview-2 data. A results comparison and accuracy estimation

2019 ◽  
pp. 89-102
Author(s):  
V. V. Kozoderov ◽  
V. D. Egorov
Keyword(s):  
Remote Sensing ◽  
Pattern Recognition ◽  
Spatial Resolution ◽  
Forest Canopy ◽  
High Spatial Resolution ◽  
Remote Sensing Data ◽  
Hyperspectral Data ◽  
Automatic Data ◽  
Sensing Data ◽  
Satellite Sensor

Pattern recognition of forest surface from remote sensing data: using the airborne hyperspectral data and using multi-bands high spatial resolution satellite sensor WorldView‑2 data are investigated. The early proposed method and standard QDA method for calculations were used. A comparison of calculations results were conducted. A recognition calculation accuracy range for airborne and satellite remote sensing data for three forest surface fragments for different created data bases for recognition system has been assessed. Some opportunities of automatic data preparing of created system were displayed. Some special features of pattern recognition of forest surfaces from hyperspectral airborne data and from multi-bands high spatial resolution satellite data were discussed.

scholarly journals Development and Validation of a Quick Sepsis-Related Organ Failure Assessment-Based Machine-Learning Model for Mortality Prediction in Patients with Suspected Infection in the Emergency Department

2020 ◽  
Vol 9 (3) ◽  
pp. 875
Author(s):  
Young Suk Kwon ◽  
Moon Seong Baek
Keyword(s):  
Machine Learning ◽  
Emergency Department ◽  
Learning Model ◽  
Gradient Boosting ◽  
Learning Models ◽  
Suspected Infection ◽  
Machine Learning Model ◽  
Failure Assessment ◽  
Qsofa Score ◽  
Machine Learning Models

The quick sepsis-related organ failure assessment (qSOFA) score has been introduced to predict the likelihood of organ dysfunction in patients with suspected infection. We hypothesized that machine-learning models using qSOFA variables for predicting three-day mortality would provide better accuracy than the qSOFA score in the emergency department (ED). Between January 2016 and December 2018, the medical records of patients aged over 18 years with suspected infection were retrospectively obtained from four EDs in Korea. Data from three hospitals (n = 19,353) were used as training-validation datasets and data from one (n = 4234) as the test dataset. Machine-learning algorithms including extreme gradient boosting, light gradient boosting machine, and random forest were used. We assessed the prediction ability of machine-learning models using the area under the receiver operating characteristic (AUROC) curve, and DeLong’s test was used to compare AUROCs between the qSOFA scores and qSOFA-based machine-learning models. A total of 447,926 patients visited EDs during the study period. We analyzed 23,587 patients with suspected infection who were admitted to the EDs. The median age of the patients was 63 years (interquartile range: 43–78 years) and in-hospital mortality was 4.0% (n = 941). For predicting three-day mortality among patients with suspected infection in the ED, the AUROC of the qSOFA-based machine-learning model (0.86 [95% CI 0.85–0.87]) for three -day mortality was higher than that of the qSOFA scores (0.78 [95% CI 0.77–0.79], p < 0.001). For predicting three-day mortality in patients with suspected infection in the ED, the qSOFA-based machine-learning model was found to be superior to the conventional qSOFA scores.

scholarly journals A Comparative Analysis of Novel Deep Learning and Ensemble Learning Models to Predict the Allergenicity of Food Proteins

Foods ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 809
Author(s):  
Liyang Wang ◽  
Dantong Niu ◽  
Xinjie Zhao ◽  
Xiaoya Wang ◽  
Mengzhen Hao ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Ensemble Learning ◽  
Food Allergen ◽  
Gradient Boosting ◽  
Learning Models ◽  
Food Proteins ◽  
Deep Model ◽  
Allergen Identification ◽  
Machine Learning Models

Traditional food allergen identification mainly relies on in vivo and in vitro experiments, which often needs a long period and high cost. The artificial intelligence (AI)-driven rapid food allergen identification method has solved the above mentioned some drawbacks and is becoming an efficient auxiliary tool. Aiming to overcome the limitations of lower accuracy of traditional machine learning models in predicting the allergenicity of food proteins, this work proposed to introduce deep learning model—transformer with self-attention mechanism, ensemble learning models (representative as Light Gradient Boosting Machine (LightGBM) eXtreme Gradient Boosting (XGBoost)) to solve the problem. In order to highlight the superiority of the proposed novel method, the study also selected various commonly used machine learning models as the baseline classifiers. The results of 5-fold cross-validation showed that the area under the receiver operating characteristic curve (AUC) of the deep model was the highest (0.9578), which was better than the ensemble learning and baseline algorithms. But the deep model need to be pre-trained, and the training time is the longest. By comparing the characteristics of the transformer model and boosting models, it can be analyzed that, each model has its own advantage, which provides novel clues and inspiration for the rapid prediction of food allergens in the future.

scholarly journals The Prediction of Hepatitis E through Ensemble Learning

2020 ◽  
Vol 18 (1) ◽  
pp. 159
Author(s):  
Tu Peng ◽  
Xiaoya Chen ◽  
Ming Wan ◽  
Lizhu Jin ◽  
Xiaofeng Wang ◽  
...  
Keyword(s):  
Water Quality ◽  
Environmental Factors ◽  
Ensemble Learning ◽  
Meteorological Data ◽  
Classical Model ◽  
Hepatitis E ◽  
Learning Model ◽  
World Health ◽  
Gradient Boosting ◽  
Percentage Error

According to the World Health Organization, about 20 million people are infected with Hepatitis E every year. In 2015, there were 44,000 deaths due to HEV infection worldwide. Food, water and climate are key factors that affect the outbreak of Hepatitis E. This paper presents an ensemble learning model for Hepatitis E prediction by studying the correlation between historical epidemic cases of hepatitis E and environmental factors (water quality and meteorological data). Environmental factors include many features, and ones that are most relevant to HEV are selected and input into the ensemble learning model composed by Gradient Boosting Decision Tree (GBDT) and Random Forest for training and prediction. Three indicators, root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE), are used to evaluate the effectiveness of the ensemble learning model against the classical time series prediction model. It is concluded that the ensemble learning model has a better prediction effect than the classical model, and the prediction effectiveness can be improved by exploiting water quality and meteorological factors (radiation, air pressure, precipitation).

scholarly journals Development of a Stope Stability Prediction Model Using Ensemble Learning Techniques - A Case Study

2020 ◽  
Vol 20 (2) ◽  
pp. 18-26
Author(s):  
F. Saadaari Saadaari ◽  
D.. Mireku-Gyimah ◽  
B. M. Olaleye
Keyword(s):  
Random Forest ◽  
Prediction Model ◽  
Ensemble Learning ◽  
Gradient Boosting ◽  
Stability Prediction ◽  
Adaptive Boosting ◽  
Bootstrap Aggregating ◽  
Learning Techniques ◽  
The Stability ◽  
Stability Graph

The consequences of collapsed stopes can be dire in the mining industry. This can lead to the revocation of a mining license in most jurisdictions, especially when the harm costs lives. Therefore, as a mine planning and technical services engineer, it is imperative to estimate the stability status of stopes. This study has attempted to produce a stope stability prediction model adopted from stability graph using ensemble learning techniques. This study was conducted using 472 case histories from 120 stopes of AngloGold Ashanti Ghana, Obuasi Mine. Random Forest, Gradient Boosting, Bootstrap Aggregating and Adaptive Boosting classification algorithms were used to produce the models. A comparative analysis was done using six classification performance metrics namely Accuracy, Precision, Sensitivity, F1-score, Specificity and Mathews Correlation Coefficient (MCC) to determine which ensemble learning technique performed best in predicting the stability of a stope. The Bootstrap Aggregating model obtained the highest MCC score of 96.84% while the Adaptive Boosting model obtained the lowest score. The Specificity scores in decreasing order of performance were 98.95%, 97.89%, 96.32% and 95.26% for Bootstrap Aggregating, Gradient Boosting, Random Forest and Adaptive Boosting respectively. The results showed equal Accuracy, Precision, F1-score and Sensitivity score of 97.89% for the Bootstrap Aggregating model while the same observation was made for Adaptive Boosting, Gradient Boosting and Random Forest with 90.53%, 92.63% and 95.79% scores respectively. At a 95% confidence interval using Wilson Score Interval, the results showed that the Bootstrap Aggregating model produced the minimal error and hence was selected as the alternative stope design tool for predicting the stability status of stopes.   Keywords: Stope Stability, Ensemble Learning Techniques, Stability Graph, Machine Learning

Multitemporal ensemble learning for snow cover extraction from high-spatial-resolution images in mountain areas

2019 ◽  
Vol 41 (5) ◽  
pp. 1668-1691
Author(s):  
Pengfeng Xiao ◽  
Chengxi Li ◽  
Luijun Zhu ◽  
Xueliang Zhang ◽  
Tengyao Ma ◽  
...  
Keyword(s):  
Snow Cover ◽  
Ensemble Learning ◽  
Spatial Resolution ◽  
High Spatial Resolution ◽  
Mountain Areas
Sign in / Sign up

Export Citation Format

Share Document