Flood Mapping Based on Multiple Endmember Spectral Mixture Analysis and Random Forest Classifier—The Case of Yuyao, China

Remote Sens. 2015, 7(9), 12539-12562; doi:10.3390/rs70912539

Author

Quanlong Feng ¹

, Jianhua Gong ^1,2

, Jiantao Liu ¹

 and Yi Li ^1,* 

¹

State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing and Digital Earth Chinese Academy of Sciences, No.20, Datun Road, Chaoyang District, 100101 Beijing, China

²

Zhejiang-CAS Application Center for Geoinformatics, No.568, Jinyang East Road, 314100 Jiashan, China

^*

Author to whom correspondence should be addressed. 

Academic Editors: Guy J-P. Schumann and Prasad S. Thenkabail

Received: 8 July 2015 / Accepted: 14 September 2015 / Published: 23 September 2015

(This article belongs to the Special Issue Remote Sensing in Flood Monitoring and Management)

View Full-Text   |     Download PDF [1663 KB, uploaded 23 September 2015]   |    

 Browse Figures

 

Abstract 

Remote sensing is recognized as a valuable tool for flood mapping due to its synoptic view and continuous coverage of the flooding event. This paper proposed a hybrid approach based on multiple endmember spectral analysis (MESMA) and Random Forest classifier to extract inundated areas in Yuyao City in China using medium resolution optical imagery. MESMA was adopted to tackle the mixing pixel problem induced by medium resolution data. Specifically, 35 optimal endmembers were selected to construct a total of 3111 models in the MESMA procedure to derive accurate fraction information. A multi-dimensional feature space was constructed including the normalized difference water index (NDWI), topographical parameters of height, slope, and aspect together with the fraction maps. A Random Forest classifier consisting of 200 decision trees was adopted to classify the post-flood image based on the above multi-features. Experimental results indicated that the proposed method can extract the inundated areas precisely with a classification accuracy of 94% and a Kappa index of 0.88. The inclusion of fraction information can help improve the mapping accuracy with an increase of 2.5%. Moreover, the proposed method also outperformed the maximum likelihood classifier and the NDWI thresholding method. This research provided a useful reference for flood mapping using medium resolution optical remote sensing imagery. View Full-Text

Keywords: flood mapping;  spectral mixture analysis;  random forest;  medium resolution imagery

▼ Figures

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

For further details log on website :
http://www.mdpi.com/2072-4292/7/9/12539

Wood–plastic composites as potential applications of recycled plastics of electronic waste and recycled particleboard

Published Date
Journal of Cleaner Production
10 May 2016, Vol.121:176–185, doi:10.1016/j.jclepro.2016.02.036

• Author 

• Philipp F. Sommerhuber ^a,,
• Tianyi Wang ^b,
• Andreas Krause ^b,1,

• aThünen Institute of Wood Research, Leuschnerstraße 91c, 21031 Hamburg, Germany
• bInstitute of Mechanical Wood Technology, Department of Wood Sciences, University of Hamburg, Leuschnerstraße 91c, 21031 Hamburg, Germany

Received 20 October 2015. Revised 19 January 2016. Accepted 6 February 2016. Available online 13 February 2016. 

Highlights

• •
  Recycled WEEE-plastics and particleboard were investigated for potential use in WPC.
• •
  Increasing wood content resulted in increased stiffness and strength of WPC.
• •
  The coupling agent SMA affected strength properties but not the stiffness of WPC.
• •
  Elementary analysis obtained content of Cd, Cr, Cu, As and Pb in recycled resources.

Abstract

Wood–plastic composites were injection-molded from recycled acrylonitrile–butadiene–styrene and polystyrene from post-consumer electronics in the interest of resource efficiency and ecological product design. The wood content was raised in two steps from 0% to 30% and 60%. Reinforcement performance of recycled particleboard was compared to virgin Norway spruce. Styrene maleic anhydride copolymer was used as the coupling agent in the composites with a 60% wood proportion to investigate the influence on interfacial adhesion. The composites were characterized by using physical and mechanical standard testing methods. Results showed increased stiffness (flexural and tensile modulus of elasticity), water uptake and density with the incorporation of wood particles to the plastic matrices. Interestingly, strength (flexural and tensile) increased as well. Wood particles from Norway spruce exhibited reinforcement in terms of strength and stiffness. The same results were achieved with particleboard particles in terms of stiffness, but the strength of the composites was negatively affected. The coupling agent affected the strength properties beneficially, which was not observed for the stiffness of the composites. The presence of cadmium, chromium, copper, arsenic and lead in the recycled resources was found by an elementary analysis. This can be linked to color pigments in recycled plastics and insufficient separation processes of recycled wood particles for particleboard production.

Keywords

Wood–plastic composites

WEEE

Waste to resource

Resource efficiency

Circular economy

Mechanical properties

---

 Table 1

Table 1.

 Table 2

Table 2.

 Table 3

Table 3.

 Table 4

Table 4.

Fig. 1.

Fig. 2.

Fig. 3.

Fig. 4.

Fig. 5.

Fig. 6.

 Table 5

Table 5.

 Table 6

Table 6.

• ∗ 
  Corresponding author. Tel.: +49 (0)40 73962 636.

For further details log on website :
http://www.sciencedirect.com/science/article/pii/S0959652616001815

Liquid by-products from wood and forest industry find use in wood-plastic composites

A novel method for adding liquid by-products from the wood industry into wood-plastic composites (WPCs) prior to manufacturing was developed in a new study from the University of Eastern Finland. The study also discovered that proton-transfer-reaction mass-spectrometry (PTR-MS) is a suitable method for measuring the amounts of volatile organic compounds, VOCs, released from WPCs.

Wood-plastic composites – replacing plastics with wood

There is an increasing need to find new alternatives for crude oil based materials such as plastics. WPCs are natural fibre composites with properties of both plastic and wood. These composites are used, for example, in buildings and in the manufacture of automobiles. It is estimated that the production of WPCs will experience an annual growth of 14% between 2014 and 2019.

Wood and plastics are very different materials in terms of their chemical properties, which is why additives are used in WPCs to enhance the compatibility of these constituents. Additives are also used to improve composites’ water absorbing and weather resistance properties, among other things. However, some additives are rather expensive and their incorporation into WPCs is not straightforward. Thus, WPCs are in need of novel and effective additives that are based on renewable resources.

Putting waste to good use – liquids separated from wood as additives in WPCs

In the study, liquid by-products generated from biochar production and heat treatment of wood were added to WPCs, and the effects of the additions on the composite properties were analysed. The findings have relevance for two different industries as the wood industry by-products are more extensively used in the WPC industry.

The findings of the study show that liquids separated from wood can be added to WPC granulates using the method developed in the study. Composites treated with liquids performed better in injection moulding and the samples of each material type were very homogeneous. Furthermore, the addition of liquids extracted from wood significantly reduced the water absorption of the composites and in some cases improved their mechanical properties.

PTR-MS gives information about VOCs quickly

The study also examined the suitability of PTR-MS for analysing the amounts of VOCs released from WPCs. The advantages of the method include a short analysis time and the opportunity to monitor the release of VOCs in real time. The study suggests that PTR-MS is a suitable method for analysing the amount of VOCs released from WPCs.

Clear and consistent differences between different WPCs and amounts of VOCs released were found using PTR-MS. For example, significant amounts of VOCs were released right after manufacturing. The amounts of VOCs released grew after the addition of liquid by-products from biochar production and heat treatment of wood; however, the emission levels of harmful compounds did not increase to a level that would be hazardous.

The findings were presented by Taneli Väisänen, MSc (Tech), in his doctoral dissertation entitled Effects Of Thermally Extracted Wood Distillates On The Characteristics Of Wood-Plastic, which is available for download at http://epublications.uef.fi/pub/urn_isbn_978-952-61-2124-6/urn_isbn_978-952-61-2124-6.pdf  

The findings were originally published in the European Journal of Wood and Wood Products, the Journal of Thermoplastic Composite Material, and the Journal of Wood Chemistry and Technology.

For further information, please contact: Taneli Väisänen, tel. +358445869472, taneli.vaisanen(at)uef.fi 

For further details log on website :
https://www.uef.fi/-/liquid-by-products-from-wood-and-forest-industry-find-use-in-wood-plastic-composites

Feature Selection of Time Series MODIS Data for Early Crop Classification Using Random Forest: A Case Study in Kansas, USA

Remote Sens. 2015, 7(5), 5347-5369; doi:10.3390/rs70505347

Author

Pengyu Hao ^1,2

, Yulin Zhan ^1,* , Li Wang ¹

, Zheng Niu ¹

 and Muhammad Shakir ¹

¹

The State Key Laboratory of Remote Sensing Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100101, China

²

University of Chinese Academy of Sciences, Beijing 100049, China

^*

Author to whom correspondence should be addressed.

Academic Editors: Tao Cheng, Zhengwei Yang, Yoshio Inoue, Yan Zhu, Weixing Cao and Prasad S. Thenkabail

Received: 29 January 2015 / Revised: 17 April 2015 / Accepted: 22 April 2015 / Published: 28 April 2015

(This article belongs to the Special Issue Recent Advances in Remote Sensing for Crop Growth Monitoring)

View Full-Text   |     Download PDF [16845 KB, uploaded 28 April 2015]   |    

 Browse Figures

 

Abstract 

Currently, accurate information on crop area coverage is vital for food security and industry, and there is strong demand for timely crop mapping. In this study, we used MODIS time series data to investigate the effect of the time series length on crop mapping. Eight time series with different lengths (ranging from one month to eight months) were tested. For each time series, we first used the Random Forest (RF) algorithm to calculate the importance score for all features (including multi-spectral data, Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and phenological metrics). Subsequently, an extension of the Jeffries–Matusita (JM) distance was used to measure class separability for each time series. Finally, the RF algorithm was used to classify crop types, and the classification accuracy and certainty were used to analyze the influence of the time series length and the number of features on classification performance; the features were added one by one based on their importance scores. Results indicated that when the time series was longer than five months, the top ten features remained stable. These features were mainly in July and August. In addition, the NDVI features contributed the majority of the most significant features for crop mapping. The NDWI and data from multi-spectral bands also contributed to improving crop mapping. On the other hand, separability, classification accuracy, and certainty increased with the number of features used and the time series length, although these values quickly reached saturation. Five months was the optimal time series length, as longer time series provided no further improvement in the classification performance. This result shows that relatively short time series have the potential to identify crops accurately, which allows for early crop mapping over large areas. View Full-Text

Keywords: time series length;  MODIS;  feature selection;  Random Forest;  classification certainty

▼ Figures

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

For further details log on website :
http://www.mdpi.com/2072-4292/7/5/5347

Mapping Robinia Pseudoacacia Forest Health Conditions by Using Combined Spectral, Spatial, and Textural Information Extracted from IKONOS Imagery and Random Forest Classifier

Remote Sens. 2015, 7(7), 9020-9044; doi:10.3390/rs70709020

Author

Hong Wang ^1,* , Yu Zhao ¹

, Ruiliang Pu ²

 and Zhenzhen Zhang ¹

¹

School of Earth Sciences and Engineering, Hohai University, No. 1 Xikang Road, Nanjing 210098, China

²

School of Geosciences, University of South Florida, 4202 E. Fowler Avenue, NES 107, Tampa, FL 33620, USA

^*

Author to whom correspondence should be addressed. 

Academic Editors: Parth Sarathi Roy and Prasad Thenkabail

Received: 22 April 2015 / Revised: 7 July 2015 / Accepted: 9 July 2015 / Published: 16 July 2015

View Full-Text   |     Download PDF [3483 KB, uploaded 16 July 2015]   |    

 Browse Figures

 

Abstract 

The textural and spatial information extracted from very high resolution (VHR) remote sensing imagery provides complementary information for applications in which the spectral information is not sufficient for identification of spectrally similar landscape features. In this study grey-level co-occurrence matrix (GLCM) textures and a local statistical analysis Getis statistic (Gi), computed from IKONOS multispectral (MS) imagery acquired from the Yellow River Delta in China, along with a random forest (RF) classifier, were used to discriminate Robina pseudoacacia tree health levels. Specifically, eight GLCM texture features (mean, variance, homogeneity, dissimilarity, contrast, entropy, angular second moment, and correlation) were first calculated from IKONOS NIR band (Band 4) to determine an optimal window size (13 × 13) and an optimal direction (45°). Then, the optimal window size and direction were applied to the three other IKONOS MS bands (blue, green, and red) for calculating the eight GLCM textures. Next, an optimal distance value (5) and an optimal neighborhood rule (Queen’s case) were determined for calculating the four Gi features from the four IKONOS MS bands. Finally, different RF classification results of the three forest health conditions were created: (1) an overall accuracy (OA) of 79.5% produced using the four MS band reflectances only; (2) an OA of 97.1% created with the eight GLCM features calculated from IKONOS Band 4 with the optimal window size of 13 × 13 and direction 45°; (3) an OA of 93.3% created with the all 32 GLCM features calculated from the four IKONOS MS bands with a window size of 13 × 13 and direction of 45°; (4) an OA of 94.0% created using the four Gi features calculated from the four IKONOS MS bands with the optimal distance value of 5 and Queen’s neighborhood rule; and (5) an OA of 96.9% created with the combined 16 spectral (four), spatial (four), and textural (eight) features. The most important feature ranked by RF classifier was GLCM texture mean calculated from Band 4, followed by Gi feature calculated from Band 4. The experimental results demonstrate that (a) both textural and spatial information was more useful than spectral information in determining the Robina pseudoacacia forest health conditions; and (b) the IKONOS NIR band was more powerful than visible bands in quantifying varying degrees of forest crown dieback. View Full-Text

Keywords: GLCM;  Getis statistic;  random forest;  forest health condition;  Robinia pseudoacacia

▼ Figures

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

For further details log on website :
http://www.mdpi.com/2072-4292/7/7/9020