Article
Environmental Sciences
Benjamin T. Fraser, Russell G. Congalton
Summary: Forest disturbances caused by pests, diseases, and other factors can lead to significant economic losses. Utilizing unmanned aerial systems (UAS) and multispectral imagery can help differentiate between different tree health statuses and improve the efficiency of collecting forestry data.
Article
Environmental Sciences
Yanchao Zhang, Wen Yang, Ying Sun, Christine Chang, Jiya Yu, Wenbo Zhang
Summary: This study examined the fusion of spectral bands information and vegetation indices for almond plantation classification using different machine learning algorithms. It was found that spectral information can be used for ground classification, with SVM performing the best among the algorithms tested. The combination of multispectral bands and vegetation indices can improve classification accuracy, with specific vegetation indices like NDEGE, NDVIG, and NDVGE showing consistent performance in enhancing accuracy.
Article
Agricultural Engineering
Rama Rao Nidamanuri, Reji Jayakumari, Anandakumar M. Ramiya, Thomas Astor, Michael Wachendorf, Andreas Buerkert
Summary: This study examines the synergistic application of high-resolution satellite imagery and terrestrial LiDAR point cloud for object-level discrimination and biophysical characterisation of crops at different nitrogen levels. Results show high accuracy in discriminating vegetable crops, but challenges in estimating biomass.
BIOSYSTEMS ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Fei Zhang, Amirhossein Hassanzadeh, Julie Kikkert, Sarah Jane Pethybridge, Jan van Aardt
Summary: This article evaluates the leaf area index (LAI) of a snap bean field using unmanned aerial system (UAS) based light detection and ranging (LiDAR) data and multispectral imagery (MSI). The results show that both LiDAR and MSI methods accurately predict LAI, with variations in effectiveness for different conditions. Additionally, MSI-based models can be more accurate than LiDAR-based models when data is collected at a consistent flight altitude, indicating the possibility of cost-effective MSI-based approaches.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Agronomy
Robert W. Bruce, Istvan Rajcan, John Sulik
Summary: Accurate determination of soybean pubescence is crucial for breeding programs and cultivar registrations, but the current visual classification method has limitations. This study utilized principal component analysis and Jeffries-Matusita distance analysis to identify pubescence classes and effective indices.
Article
Environmental Sciences
Robert Chancia, Jan van Aardt, Sarah Pethybridge, Daniel Cross, John Henderson
Summary: Timely and accurate monitoring can streamline crop management, harvest planning, and processing in New York's table beet industry. By utilizing unmanned aerial systems and multispectral imaging, researchers were able to predict table beet yield components effectively by pairing reflectance bands and canopy area. The study showed promising results for root count and mass prediction using imagery from emergence and canopy closure stages, highlighting the importance of early canopy growth area for accurate yield estimation.
Article
Environmental Sciences
Brindusa Cristina Budei, Benoit St-Onge, Richard A. A. Fournier, Daniel Kneeshaw
Summary: Identifying tree species using multispectral lidar can improve forest management decision-making, but the influence of scan angle on classification accuracy needs to be evaluated. This study found that the correlation between feature values and scan angle was poor, with minimal impact on species classification accuracy.
Article
Environmental Sciences
Sani Success Ojogbane, Shattri Mansor, Bahareh Kalantar, Zailani Bin Khuzaimah, Helmi Zulhaidi Mohd Shafri, Naonori Ueda
Summary: A novel network based on an end-to-end deep learning framework is proposed for detecting and classifying urban building features, achieving an overall accuracy of over 80%. Morphological operations applied to extracted building footprints have improved the uniformity of building boundaries for increased accuracy in detecting buildings.
Article
Forestry
Jian Xing, Chaoyong Wang, Ying Liu, Zibo Chao, Jiabo Guo, Haitao Wang, Xinfang Chang
Summary: In this paper, a UAV-based method for predicting forest surface dead fuel moisture content (DFMC) is proposed. By using a multispectral camera and deep-learning algorithm, the large-scale prediction of DFMC on the forest surface is achieved. The results from field tests in Harbin, China show that the proposed method can accurately predict the moisture content of dead combustible material with high precision.
Review
Environmental Sciences
Maja Michalowska, Jacek Rapinski
Summary: Remote sensing techniques, especially Light Detection and Ranging (LiDAR), have greatly improved large-scale forest inventory by providing three-dimensional point cloud data for object extraction and classification. Various LiDAR-derived metrics, combined with classification algorithms, contribute to high accuracy in tree species discrimination. Full-waveform data extraction and the use of random forest or support vector machine classifiers have shown to be most effective in increasing species discrimination performance.
Article
Environmental Sciences
Qian Guo, Jian Zhang, Shijie Guo, Zhangxi Ye, Hui Deng, Xiaolong Hou, Houxi Zhang
Summary: This study establishes an efficient and practical method for urban tree identification by combining an object-oriented approach and a random forest algorithm using UAV multispectral images. The results show that the random forest classifier performs better than SVM and KNN classifiers. Spectral features are the most important type of features, followed by index features, texture features and geometric features. The accuracy of Camphor and Cinnamomum Japonicum is lower than that of other tree species, suggesting the need to add additional features in the future to improve accuracy.
Article
Engineering, Electrical & Electronic
Svetlana Illarionova, Alexey Trekin, Vladimir Ignatiev, Ivan Oseledets
Summary: By utilizing multispectral satellite imagery and neural networks, the forest classification problem was addressed as an image segmentation task, represented as a hierarchical set of binary classification tasks, to achieve better results.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Geochemistry & Geophysics
Ronny Haensch, Olaf Hellwich
Summary: This letter introduces a novel node testing method within the random forest framework for urban area monitoring, which can be applied to various sensors. It not only provides accurate classification results, but also helps to determine which sensor data is most meaningful for solving the classification task, outperforming deep learning approaches on a public benchmark data set despite using only a small fraction of training samples.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Forestry
Benjamin T. Fraser, Russell G. Congalton
Summary: The study compared visual interpretation and digital processing for forest plot composition and individual tree identification, finding that digital processing had higher accuracy in detecting individual trees and improved overall accuracy for forest composition.
Article
Geography, Physical
Kathrin Maier, Andrea Nascetti, Ward van Pelt, Gunhild Rosqvist
Summary: This study proposes a novel method to determine the spatial distribution of snow depth in challenging alpine terrains using a combination of a multispectral camera and a UAV. The method enables fast, reliable, and affordable measurement of high-resolution 3D snow-covered surface models. The experiments suggest that the red components in the electromagnetic spectrum are crucial in photogrammetric processing, and applying Principal Component Analysis can reduce processing times and computational resources.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2022)
Article
Geography, Physical
Fashuai Li, Matti Lehtomaki, Sander Oude Elberink, George Vosselman, Antero Kukko, Eetu Puttonen, Yuwei Chen, Juha Hyyppa
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2019)
Article
Environmental Sciences
Hui Shao, Yuwei Chen, Zhirong Yang, Changhui Jiang, Wei Li, Haohao Wu, Shaowei Wang, Fan Yang, Jie Chen, Eetu Puttonen, Juha Hyyppa
Article
Geochemistry & Geophysics
Hui Shao, Yuwei Chen, Zirong Yang, Changhui Jiang, Wei Li, Haohao Wu, Zhijie Wen, Shaowei Wang, Eetu Puttonen, Juha Hyyppa
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2020)
Article
Remote Sensing
Changhui Jiang, Yuwei Chen, Wenxin Tian, Haohao Wu, Wei Li, Hui Zhou, Hui Shao, Shaojing Song, Eetu Puttonen, Juha Hyyppa
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2020)
Article
Plant Sciences
Mariana Batista Campos, Paula Litkey, Yunsheng Wang, Yuwei Chen, Heikki Hyyti, Juha Hyyppa, Eetu Puttonen
Summary: TLS technology is commonly used for vegetation dynamics monitoring, but its potential for monitoring long-term temporal phenomena in fully grown trees has not been fully explored. This study presents an automated and permanent TLS measurement station at a boreal forestry field station to monitor short- and long-term phenological changes.
FRONTIERS IN PLANT SCIENCE
(2021)
Article
Agronomy
Monica Herrero-Huerta, Alexander Bucksch, Eetu Puttonen, Katy M. Rainey
Article
Environmental Sciences
S. Junttila, T. Holtta, E. Puttonen, M. Katoh, M. Vastaranta, H. Kaartinen, M. Holopainen, H. Hyyppa
Summary: Extreme events in the past decades have led to an increase in drought-induced plant mortality globally. Timely information on plant water dynamics is crucial for understanding and predicting such mortality. Research has shown that using terrestrial laser scanning (TLS) intensity measurements can capture a significant portion of diurnal variation in leaf water potential (Psi(L)), enhancing our understanding of plant water dynamics.
REMOTE SENSING OF ENVIRONMENT
(2021)
Article
Environmental Sciences
Jianxin Jia, Changhui Jiang, Wei Li, Haohao Wu, Yuwei Chen, Peilun Hu, Hui Shao, Shaowei Wang, Fan Yang, Eetu Puttonen, Juha Hyyppa
Summary: A hyperspectral LiDAR with wide-range wavelength was developed for vegetation spectral data acquisition, parameter extraction, and classification, showing great potential in precision agriculture application.
Article
Multidisciplinary Sciences
Santosh Hiremath, Samantha Wittke, Taru Palosuo, Jere Kaivosoja, Fulu Tao, Maximilian Proll, Eetu Puttonen, Pirjo Peltonen-Sainio, Pekka Marttinen, Hiroshi Mamitsuka
Summary: This study investigates the feasibility of using satellite images and machine learning models to classify agricultural field parcels into those with and without crop loss. Despite the poor quality of data, the random forest model shows promising results in identifying new crop-loss fields based on reference fields of the same year. There is potential for various applications in efficient agricultural monitoring and verifying crop-loss claims.
Article
Remote Sensing
Haibin Sun, Zhen Wang, Yuwei Chen, Wenxin Tian, Wenjing He, Haohao Wu, Huijing Zhang, Lingli Tang, Changhui Jiang, Jianxin Jia, Zhiyong Duan, Hui Zhou, Eetu Puttonen, Juha Hyyppa
Summary: This study proposed and tested an eight-channel Hyperspectral LiDAR prototype covering visible to short-wavelength infrared range. The results showed that the prototype is capable of effectively obtaining spectral profiles of plants, textiles, camouflage objects, and ore samples, with potential applications in vegetation, mining, and surveillance related object classification.
EUROPEAN JOURNAL OF REMOTE SENSING
(2022)
Article
Forestry
Samuli Junttila, Mariana Campos, Teemu Holtta, Lauri Lindfors, Aimad El Issaoui, Mikko Vastaranta, Hannu Hyyppa, Eetu Puttonen
Summary: In this study, the movement of tree branches was analyzed in a long-term drought experiment and at a circadian time scale. The results showed a strong correlation between branch movement and leaf water status, supporting the hypothesis that changes in leaf and branch water status can cause branch movements. These findings are important for monitoring and understanding the water relations of tree communities.
Article
Environmental Sciences
Maria Yli-Heikkila, Samantha Wittke, Markku Luotamo, Eetu Puttonen, Mika Sulkava, Petri Pellikka, Janne Heiskanen, Arto Klami
Summary: One of the key principles of food security is to ensure the proper functioning of global food markets. This study proposes a method for large-scale crop yield estimations using satellite image time series, and demonstrates that a deep learning-based temporal convolutional network outperforms traditional machine learning methods and national crop forecasts in accuracy. The study also shows that mean-aggregated regional predictions with histogram-based features calculated from farm-level observations perform better than other tested approaches.
Article
Computer Science, Software Engineering
Samantha Wittke, Anne Fouilloux, Petteri Lehti, Juuso Varho, Arttu Kivimaki, Maiju Karhu, Mika Karjalainen, Matti Vaaja, Eetu Puttonen
Summary: This article introduces a toolkit called EODIE that extracts object-level time-series information from multiple multispectral satellite remote sensing platforms and produces analysis-ready products for subsequent data analysis.
Article
Remote Sensing
Di Wang, Eetu Puttonen, Eric Casella
Summary: This study presents PlantMove, a fully automatic tool for quantifying 3D motion fields of plant structural movements using TLS point clouds. The method demonstrates high accuracy and efficiency in handling large datasets with complex structures. It has been successfully applied to synthetic plant datasets as well as real TLS data to detect circadian rhythms and growth patterns in plants.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2022)
Article
Engineering, Aerospace
Changhui Jiang, Yuwei Chen, Wenxin Tian, Ziyi Feng, Wei Li, Chunchen Zhou, Hui Shao, Eetu Puttonen, Juha Hyyppa
SATELLITE NAVIGATION
(2020)
