Estimating ground-level PM2.5 using micro-satellite images by a convolutional neural network and random forest approach

2020 ◽  
Vol 230 ◽  
pp. 117451 ◽  
Author(s):  
Tongshu Zheng ◽  
Michael H. Bergin ◽  
Shijia Hu ◽  
Joshua Miller ◽  
David E. Carlson
Keyword(s):  
Neural Network ◽  
Random Forest ◽  
Convolutional Neural Network ◽  
Satellite Images ◽  
Ground Level

scholarly journals Deep Convolutional Neural Network for Mapping Smallholder Agriculture Using High Spatial Resolution Satellite Image

Sensors ◽  
2019 ◽  
Vol 19 (10) ◽  
pp. 2398 ◽  
Author(s):  
Bin Xie ◽  
Hankui K. Zhang ◽  
Jie Xue
Keyword(s):  
Neural Network ◽  
Random Forest ◽  
Land Cover ◽  
Convolutional Neural Network ◽  
Satellite Images ◽  
Spatial Information ◽  
Deep Convolutional Neural Network ◽  
Crop Types ◽  
Pooling Strategy

In classification of satellite images acquired over smallholder agricultural landscape with complex spectral profiles of various crop types, exploring image spatial information is important. The deep convolutional neural network (CNN), originally designed for natural image recognition in the computer vision field, can automatically explore high level spatial information and thus is promising for such tasks. This study tried to evaluate different CNN structures for classification of four smallholder agricultural landscapes in Heilongjiang, China using pan-sharpened 2 m GaoFen-1 (meaning high resolution in Chinese) satellite images. CNN with three pooling strategies: without pooling, with max pooling and with average pooling, were evaluated and compared with random forest. Two different numbers (~70,000 and ~290,000) of CNN learnable parameters were examined for each pooling strategy. The training and testing samples were systematically sampled from reference land cover maps to ensure sample distribution proportional to the reference land cover occurrence and included 60,000–400,000 pixels to ensure effective training. Testing sample classification results in the four study areas showed that the best pooling strategy was the average pooling CNN and that the CNN significantly outperformed random forest (2.4–3.3% higher overall accuracy and 0.05–0.24 higher kappa coefficient). Visual examination of CNN classification maps showed that CNN can discriminate better the spectrally similar crop types by effectively exploring spatial information. CNN was still significantly outperformed random forest using training samples that were evenly distributed among classes. Furthermore, future research to improve CNN performance was discussed.

scholarly journals Local PM2.5 Hotspot Detector at 300 m Resolution: A Random Forest–Convolutional Neural Network Joint Model Jointly Trained on Satellite Images and Meteorology

2021 ◽  
Vol 13 (7) ◽  
pp. 1356
Author(s):  
Tongshu Zheng ◽  
Michael Bergin ◽  
Guoyin Wang ◽  
David Carlson
Keyword(s):  
Neural Network ◽  
Random Forest ◽  
Convolutional Neural Network ◽  
Satellite Imagery ◽  
Urban Landscape ◽  
Ground Level ◽  
Absolute Error ◽  
Joint Model ◽  
Local Contrast ◽  
Pixel Resolution

Satellite-based rapid sweeping screening of localized PM2.5 hotspots at fine-scale local neighborhood levels is highly desirable. This motivated us to develop a random forest–convolutional neural network–local contrast normalization (RF–CNN–LCN) pipeline that detects local PM2.5 hotspots at a 300 m resolution using satellite imagery and meteorological information. The RF–CNN joint model in the pipeline uses three meteorological variables and daily 3 m/pixel resolution PlanetScope satellite imagery to generate daily 300 m ground-level PM2.5 estimates. The downstream LCN processes the estimated PM2.5 maps to reveal local PM2.5 hotspots. The RF–CNN joint model achieved a low normalized root mean square error for PM2.5 of within ~31% and normalized mean absolute error of within ~19% on the holdout samples in both Delhi and Beijing. The RF–CNN–LCN pipeline reasonably predicts urban PM2.5 local hotspots and coolspots by capturing both the main intra-urban spatial trends in PM2.5 and the local variations in PM2.5 with urban landscape, with local hotspots relating to compact urban spatial structures and coolspots being open areas and green spaces. Based on 20 sampled representative neighborhoods in Delhi, our pipeline revealed an annual average 9.2 ± 4.0 μg m−3 difference in PM2.5 between the local hotspots and coolspots within the same community. In some cases, the differences were much larger; for example, at the Indian Gandhi International Airport, the increase was 20.3 μg m−3 from the coolest spot (the residential area immediately outside the airport) to the hottest spot (airport runway). This work provides a possible means of automatically identifying local PM2.5 hotspots at 300 m in heavily polluted megacities and highlights the potential existence of substantial health inequalities in long-term outdoor PM2.5 exposures even within the same local neighborhoods between local hotspots and coolspots.

scholarly journals CNN Algorithm for Roof Detection and Material Classification in Satellite Images

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1592
Author(s):  
Jonguk Kim ◽  
Hyansu Bae ◽  
Hyunwoo Kang ◽  
Suk Gyu Lee
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Satellite Imagery ◽  
Satellite Images ◽  
External Shocks ◽  
Satellite Imaging ◽  
Material Classification ◽  
Model Algorithm ◽  
Great Damage

This paper suggests an algorithm for extracting the location of a building from satellite imagery and using that information to modify the roof content. The materials are determined by measuring the conditions where the building is located and detecting the position of a building in broad satellite images. Depending on the incomplete roof or material, there is a greater possibility of great damage caused by disaster situations or external shocks. To address these problems, we propose an algorithm to detect roofs and classify materials in satellite images. Satellite imaging locates areas where buildings are likely to exist based on roads. Using images of the detected buildings, we classify the material of the roof using a proposed convolutional neural network (CNN) model algorithm consisting of 43 layers. In this paper, we propose a CNN structure to detect areas with buildings in large images and classify roof materials in the detected areas.

scholarly journals Deep Learning-Based Classification of Weld Surface Defects

2019 ◽  
Vol 9 (16) ◽  
pp. 3312 ◽  
Author(s):  
Zhu ◽  
Ge ◽  
Liu
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Random Forest ◽  
Convolutional Neural Network ◽  
Surface Defects ◽  
Recognition Method ◽  
High Level ◽  
Intelligent Recognition ◽  
Non Destructive

In order to realize the non-destructive intelligent identification of weld surface defects, an intelligent recognition method based on deep learning is proposed, which is mainly formed by convolutional neural network (CNN) and forest random. First, the high-level features are automatically learned through the CNN. Random forest is trained with extracted high-level features to predict the classification results. Secondly, the weld surface defects images are collected and preprocessed by image enhancement and threshold segmentation. A database of weld surface defects is established using pre-processed images. Finally, comparative experiments are performed on the weld surface defects database. The results show that the accuracy of the method combined with CNN and random forest can reach 0.9875, and it also demonstrates the method is effective and practical.

Predict plant-derived xenomiRs from plant miRNA sequences using random forest and one-dimensional convolutional neural network models

2018 ◽  
Author(s):  
Qi Zhao ◽  
Qian Mao ◽  
Zheng Zhao ◽  
Tongyi Dou ◽  
Zhiguo Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Random Forest ◽  
Convolutional Neural Network ◽  
Human Body ◽  
Expression Profiles ◽  
Mirna Sequence ◽  
Selective Absorption ◽  
Sequence Specificity ◽  
One Dimensional ◽  
Plant Mirna

AbstractBackgroundAn increasing number of studies reported that exogenous miRNAs (xenomiRs) can be detected in animal bodies, however, some others reported negative results. Some attributed this divergence to the selective absorption of plant-derived xenomiRs by animals.ResultsHere, we analyzed 166 plant-derived xenomiRs reported in our previous study and 942 non-xenomiRs extracted from miRNA expression profiles of four species of commonly consumed plants. Employing statistics analysis and cluster analysis, our study revealed the potential sequence specificity of plant-derived xenomiRs. Furthermore, a random forest model and a one-dimensional convolutional neural network model were trained using miRNA sequence features and raw miRNA sequences respectively and then employed to predict unlabeled plant miRNAs in miRBase. A total of 241 possible plant-derived xenomiRs were predicted by both models. Finally, the potential functions of these possible plant-derived xenomiRs along with our previously reported ones in human body were analyzed.ConclusionsOur study, for the first time, presents the systematic plant-derived xenomiR sequences analysis and provides evidence for selective absorption of plant miRNA by human body, which could facilitate the future investigation about the mechanisms underlying the transference of plant-derived xenomiR.

scholarly journals Tree Species Classification Based on Hybrid Ensembles of a Convolutional Neural Network (CNN) and Random Forest Classifiers

2019 ◽  
Vol 11 (23) ◽  
pp. 2788 ◽  
Author(s):  
Uwe Knauer ◽  
Cornelius Styp von Rekowski ◽  
Marianne Stecklina ◽  
Tilman Krokotsch ◽  
Tuan Pham Minh ◽  
...  
Keyword(s):  
Neural Network ◽  
Random Forest ◽  
Convolutional Neural Network ◽  
Tree Species ◽  
Classification Performance ◽  
Majority Voting ◽  
Imaging Data ◽  
Species Classification ◽  
Weighted Voting ◽  
Linear Discriminant

In this paper, we evaluate different popular voting strategies for fusion of classifier results. A convolutional neural network (CNN) and different variants of random forest (RF) classifiers were trained to discriminate between 15 tree species based on airborne hyperspectral imaging data. The spectral data was preprocessed with a multi-class linear discriminant analysis (MCLDA) as a means to reduce dimensionality and to obtain spatial–spectral features. The best individual classifier was a CNN with a classification accuracy of 0.73 +/− 0.086. The classification performance increased to an accuracy of 0.78 +/− 0.053 by using precision weighted voting for a hybrid ensemble of the CNN and two RF classifiers. This voting strategy clearly outperformed majority voting (0.74), accuracy weighted voting (0.75), and presidential voting (0.75).

Sign in / Sign up

Export Citation Format

Share Document