Wide-area shrub forest map based on multi-sensor data and active learning

2021 ◽  
Author(s):  
Marius Rüetschi ◽  
Dominique Weber ◽  
Tiziana L. Koch ◽  
David Small ◽  
Lars T. Waser
Keyword(s):  
Remote Sensing ◽  
Active Learning ◽  
Training Data ◽  
Swiss Alps ◽  
Sensor Data ◽  
Aerial Image ◽  
Validation Data ◽  
Vegetation Height ◽  
Learning Techniques ◽  
Shrub Forest

<p>In the past few decades, the occurrence of shrub forest dominated by the two species Green alder (Alnus viridis) and Dwarf mountain pine (Pinus mugo) has increased in the Swiss Alps. Up-to-date and area-wide information on its distribution is required for countrywide forest reporting (5 % of Swiss forest consists of shrub forest) and of great interest to the forestry sector. Such information helps to better understand forest succession and supports the evaluation and management of protection forests. Until now, this information has been based on estimates from the Swiss National Forest Inventory (NFI). Due to their sampling scheme that uses a regular grid, these data are not area-wide maps. However, new developments in remote sensing techniques in combination with high spatial and temporal resolution data have facilitated the production of maps over large areas, e.g. the whole of Switzerland (41’285 km<sup>2</sup>).</p><p>To map the shrub forest areas, we developed an approach that uses a Random Forest (RF) model, active learning techniques and data from multiple remote sensing sources. The training data was produced via aerial image interpretation of areas covered by shrub forest. We used predictor data from different sensors and technologies, complementing each other by their diverse sensitivity to properties of shrub forests. These data included airborne Digital Terrain (DTM) and Vegetation Height Models (VHM), and spaceborne Synthetic Aperture Radar (SAR) backscatter from the Sentinel-1 constellation and multispectral imagery from Sentinel-2. To improve mapping quality, an iterative and semi-automatic active learning technique was used to generate further training data.</p><p>The above outlined workflow enabled the production of a shrub forest map for the whole of Switzerland with a spatial resolution of 10 m. An accuracy assessment was performed using independent validation data of a total of 7’640 regularly distributed NFI plots. Mean shrub forest cover per plot (50 m x 50 m) was slightly underestimated by 1.5 % with a root mean square error of 10 %. The influence of the active learning was observed and revealed higher accuracies after each additional iteration of training data production. The proposed approach underscores the potential of multi-sensor data combined with active learning techniques to provide cost-effective and area-wide information on the occurrence of shrub forest in a manner complementary to the NFI measurements.</p>

scholarly journals THE SEN1-2 DATASET FOR DEEP LEARNING IN SAR-OPTICAL DATA FUSION

2018 ◽  
Vol IV-1 ◽  
pp. 141-146 ◽  
Author(s):  
M. Schmitt ◽  
L. H. Hughes ◽  
X. X. Zhu
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Data Fusion ◽  
Training Data ◽  
Sensor Data ◽  
Optical Data ◽  
Multiple Sensors ◽  
Optical Images ◽  
Multi Sensor Data Fusion ◽  
Learning Techniques

<p><strong>Abstract.</strong> While deep learning techniques have an increasing impact on many technical fields, gathering sufficient amounts of training data is a challenging problem in remote sensing. In particular, this holds for applications involving data from multiple sensors with heterogeneous characteristics. One example for that is the fusion of synthetic aperture radar (SAR) data and optical imagery. With this paper, we publish the <i>SEN1-2</i> dataset to foster deep learning research in SAR-optical data fusion. <i>SEN1-2</i> comprises 282;384 pairs of corresponding image patches, collected from across the globe and throughout all meteorological seasons. Besides a detailed description of the dataset, we show exemplary results for several possible applications, such as SAR image colorization, SAR-optical image matching, and creation of artificial optical images from SAR input data. Since <i>SEN1-2</i> is the first large open dataset of this kind, we believe it will support further developments in the field of deep learning for remote sensing as well as multi-sensor data fusion.</p>

Application of multi-sensor unmanned aerial system for identification of hydrothermal alteration zones

2020 ◽  
Author(s):  
Yosoon Choi ◽  
Jieun Baek ◽  
Jangwon Suh ◽  
Sung-Min Kim
Keyword(s):  
Machine Learning ◽  
Classification Accuracy ◽  
Training Data ◽  
Sensor Data ◽  
Machine Learning Techniques ◽  
Integrated Analysis ◽  
Unmanned Aerial System ◽  
Data Sets ◽  
Learning Techniques ◽  
Hydrothermal Alteration Zones

&lt;p&gt;In this study, we proposed a method to utilize a multi-sensor Unmanned Aerial System (UAS) for exploration of hydrothermal alteration zones. This study selected an area (10m &amp;#215; 20m) composed mainly of the andesite and located on the coast, with wide outcrops and well-developed structural and mineralization elements. Multi-sensor (visible, multispectral, thermal, magnetic) data were acquired in the study area using UAS, and were studied using machine learning techniques. For utilizing the machine learning techniques, we applied the stratified random method to sample 1000 training data in the hydrothermal zone and 1000 training data in the non-hydrothermal zone identified through the field survey. The 2000 training data sets created for supervised learning were first classified into 1500 for training and 500 for testing. Then, 1500 for training were classified into 1200 for training and 300 for validation. The training and validation data for machine learning were generated in five sets to enable cross-validation. Five types of machine learning techniques were applied to the training data sets: k-Nearest Neighbors (k-NN), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), and Deep Neural Network (DNN). As a result of integrated analysis of multi-sensor data using five types of machine learning techniques, RF and SVM techniques showed high classification accuracy of about 90%. Moreover, performing integrated analysis using multi-sensor data showed relatively higher classification accuracy in all five machine learning techniques than analyzing magnetic sensing data or single optical sensing data only.&lt;/p&gt;

scholarly journals Grossflächige Klassifikation von Gebüschwald mit Fernerkundungsdaten

2020 ◽  
Vol 171 (2) ◽  
pp. 51-59
Author(s):  
Dominique Weber ◽  
Marius Rüetschi ◽  
David Small ◽  
Christian Ginzler
Keyword(s):  
Remote Sensing ◽  
Large Scale ◽  
Learning Algorithm ◽  
Remote Sensing Data ◽  
Aerial Imagery ◽  
Sensing Data ◽  
Vegetation Height ◽  
Green Alder ◽  
Mountain Pine ◽  
Shrub Forest

Large-scale classification of shrub forest with remote sensing data Information on shrub forest distribution and development is important for a range of forestry- and ecologically-related questions, but current and area-wide datasets have been characterized by limited availability. In this study, the mapping of shrub forests dominated by green alder, mountain pine and hazel for the canton of Grison was investigated, based on available nationwide remote sensing data. Satellite data from Sentinel-1 and Sentinel-2, as well as a vegetation height and an elevation model were used. Training areas provided by the canton and supplemented by aerial imagery interpretation were used for a supervised classification with Random Forest, a decision tree-based machine learning algorithm. Independent validation of the results was carried out with data from the National Forest Inventory (NFI). Green alder and mountain pine forests were classified with high accuracy of 92.1% respectively 86.7%, whereas for hazel shrub forests, the internal model accuracy was only 66.7%. The resulting area expansion of the shrub forest was comparable with findings based on the NFI. A direct comparison with the NFI aerial imagery interpretation points revealed major discrepancies. The main reason for this is the different degree of spatial detail. However, NFI areas with a high percentage of shrubs were reliably classified as shrub forest. The method presented here underscores the potential of remote sensing data available throughout Switzerland for an essentially objective, costefficient and large-scale mapping of shrub forests with an accuracy applicable in practice.

scholarly journals CONCEPT FOR A COMPOUND ANALYSIS IN ACTIVE LEARNING FOR REMOTE SENSING

2015 ◽  
Vol XL-3/W2 ◽  
pp. 273-279 ◽  
Author(s):  
S. Wuttke ◽  
W. Middelmann ◽  
U. Stilla
Keyword(s):  
Remote Sensing ◽  
Active Learning ◽  
Supervised Classification ◽  
Early Stage ◽  
Ground Truth ◽  
Training Sample ◽  
Ground Truth Data ◽  
Training Costs ◽  
Learning Techniques

Active learning reduces training costs for supervised classification by acquiring ground truth data only for the most useful samples. We present a new concept for the analysis of active learning techniques. Our framework is split into an outer and an inner view to facilitate the assignment of different influences. The main contribution of this paper is a concept of a new compound analysis in the active learning loop. It comprises three sub-analyses: structural, oracle, prediction. They are combined to form a hypothesis of the usefulness for each unlabeled training sample. Though the analysis is in an early stage, different extensions are highlighted. Further we show how variations inside the framework lead to many techniques from the active learning literature. In this work we focus on remote sensing, but the proposed method can be applied to other fields as well.

scholarly journals Semantic Multigranularity Feature Learning for High-Resolution Remote Sensing Image Scene Classification

2021 ◽  
Vol 11 (19) ◽  
pp. 9204
Author(s):  
Xinyi Ma ◽  
Zhifeng Xiao ◽  
Hong-sik Yun ◽  
Seung-Jun Lee
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Spatial Information ◽  
Feature Learning ◽  
Remote Sensing Image ◽  
Input Image ◽  
Training Data ◽  
Aerial Image ◽  
Scene Classification ◽  
Feature Maps

High-resolution remote sensing image scene classification is a challenging visual task due to the large intravariance and small intervariance between the categories. To accurately recognize the scene categories, it is essential to learn discriminative features from both global and local critical regions. Recent efforts focus on how to encourage the network to learn multigranularity features with the destruction of the spatial information on the input image at different scales, which leads to meaningless edges that are harmful to training. In this study, we propose a novel method named Semantic Multigranularity Feature Learning Network (SMGFL-Net) for remote sensing image scene classification. The core idea is to learn both global and multigranularity local features from rearranged intermediate feature maps, thus, eliminating the meaningless edges. These features are then fused for the final prediction. Our proposed framework is compared with a collection of state-of-the-art (SOTA) methods on two fine-grained remote sensing image scene datasets, including the NWPU-RESISC45 and Aerial Image Datasets (AID). We justify several design choices, including the branch granularities, fusion strategies, pooling operations, and necessity of feature map rearrangement through a comparative study. Moreover, the overall performance results show that SMGFL-Net consistently outperforms other peer methods in classification accuracy, and the superiority is more apparent with less training data, demonstrating the efficacy of feature learning of our approach.

scholarly journals $$L^*$$-based learning of Markov decision processes (extended version)

2021 ◽  
Author(s):  
Martin Tappler ◽  
Bernhard K. Aichernig ◽  
Giovanni Bacci ◽  
Maria Eichlseder ◽  
Kim G. Larsen
Keyword(s):  
Active Learning ◽  
Learning Strategies ◽  
Markov Decision Processes ◽  
Learning Algorithm ◽  
Decision Processes ◽  
Training Data ◽  
Passive Learning ◽  
Learning Techniques ◽  
System Logs ◽  
Markov Decision

AbstractAutomata learning techniques automatically generate systemmodels fromtest observations. Typically, these techniques fall into two categories: passive and active. On the one hand, passive learning assumes no interaction with the system under learning and uses a predetermined training set, e.g., system logs. On the other hand, active learning techniques collect training data by actively querying the system under learning, allowing one to steer the discovery ofmeaningful information about the systemunder learning leading to effective learning strategies. A notable example of active learning technique for regular languages is Angluin’s $$L^*$$ L ∗ -algorithm. The $$L^*$$ L ∗ -algorithm describes the strategy of a student who learns the minimal deterministic finite automaton of an unknown regular language $$L$$ L by asking a succinct number of queries to a teacher who knows $$L$$ L .In this work, we study $$L^*$$ L ∗ -based learning of deterministic Markov decision processes, a class of Markov decision processes where an observation following an action uniquely determines a successor state. For this purpose, we first assume an ideal setting with a teacher who provides perfect information to the student. Then, we relax this assumption and present a novel learning algorithm that collects information by sampling execution traces of the system via testing.Experiments performed on an implementation of our sampling-based algorithm suggest that our method achieves better accuracy than state-of-the-art passive learning techniques using the same amount of test obser vations. In contrast to existing learning algorithms which assume a predefined number of states, our algorithm learns the complete model structure including the state space.

Comparative Analysis of Machine Learning Techniques Using Predictive Modeling

2020 ◽  
Vol 13 ◽  
Author(s):  
Ritu Khandelwal ◽  
Hemlata Goyal ◽  
Rajveer Singh Shekhawat
Keyword(s):  
Machine Learning ◽  
Comparative Analysis ◽  
Data Science ◽  
Training Data ◽  
Machine Learning Techniques ◽  
Future Trends ◽  
Data Set ◽  
Learning Stage ◽  
Learning Techniques ◽  
Different Types

Introduction: Machine learning is an intelligent technology that works as a bridge between businesses and data science. With the involvement of data science, the business goal focuses on findings to get valuable insights on available data. The large part of Indian Cinema is Bollywood which is a multi-million dollar industry. This paper attempts to predict whether the upcoming Bollywood Movie would be Blockbuster, Superhit, Hit, Average or Flop. For this Machine Learning techniques (classification and prediction) will be applied. To make classifier or prediction model first step is the learning stage in which we need to give the training data set to train the model by applying some technique or algorithm and after that different rules are generated which helps to make a model and predict future trends in different types of organizations. Methods: All the techniques related to classification and Prediction such as Support Vector Machine(SVM), Random Forest, Decision Tree, Naïve Bayes, Logistic Regression, Adaboost, and KNN will be applied and try to find out efficient and effective results. All these functionalities can be applied with GUI Based workflows available with various categories such as data, Visualize, Model, and Evaluate. Result: To make classifier or prediction model first step is learning stage in which we need to give the training data set to train the model by applying some technique or algorithm and after that different rules are generated which helps to make a model and predict future trends in different types of organizations Conclusion: This paper focuses on Comparative Analysis that would be performed based on different parameters such as Accuracy, Confusion Matrix to identify the best possible model for predicting the movie Success. By using Advertisement Propaganda, they can plan for the best time to release the movie according to the predicted success rate to gain higher benefits. Discussion: Data Mining is the process of discovering different patterns from large data sets and from that various relationships are also discovered to solve various problems that come in business and helps to predict the forthcoming trends. This Prediction can help Production Houses for Advertisement Propaganda and also they can plan their costs and by assuring these factors they can make the movie more profitable.

scholarly journals Improved SinGAN Integrated with an Attentional Mechanism for Remote Sensing Image Classification

2021 ◽  
Vol 13 (9) ◽  
pp. 1713
Author(s):  
Songwei Gu ◽  
Rui Zhang ◽  
Hongxia Luo ◽  
Mengyao Li ◽  
Huamei Feng ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Real Life ◽  
Attention Mechanism ◽  
Training Data ◽  
Generative Adversarial Networks ◽  
Natural Image ◽  
Remote Sensing Images ◽  
Training Time ◽  
Adversarial Networks ◽  
Remote Sensing Image Classification

Deep learning is an important research method in the remote sensing field. However, samples of remote sensing images are relatively few in real life, and those with markers are scarce. Many neural networks represented by Generative Adversarial Networks (GANs) can learn from real samples to generate pseudosamples, rather than traditional methods that often require more time and man-power to obtain samples. However, the generated pseudosamples often have poor realism and cannot be reliably used as the basis for various analyses and applications in the field of remote sensing. To address the abovementioned problems, a pseudolabeled sample generation method is proposed in this work and applied to scene classification of remote sensing images. The improved unconditional generative model that can be learned from a single natural image (Improved SinGAN) with an attention mechanism can effectively generate enough pseudolabeled samples from a single remote sensing scene image sample. Pseudosamples generated by the improved SinGAN model have stronger realism and relatively less training time, and the extracted features are easily recognized in the classification network. The improved SinGAN can better identify sub-jects from images with complex ground scenes compared with the original network. This mechanism solves the problem of geographic errors of generated pseudosamples. This study incorporated the generated pseudosamples into training data for the classification experiment. The result showed that the SinGAN model with the integration of the attention mechanism can better guarantee feature extraction of the training data. Thus, the quality of the generated samples is improved and the classification accuracy and stability of the classification network are also enhanced.

scholarly journals Ablation Analysis to Select Wearable Sensors for Classifying Standing, Walking, and Running

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 194
Author(s):  
Sarah Gonzalez ◽  
Paul Stegall ◽  
Harvey Edwards ◽  
Leia Stirling ◽  
Ho Chit Siu
Keyword(s):  
Activity Recognition ◽  
Principal Components ◽  
Classification Accuracy ◽  
Wearable Sensors ◽  
Sensor Data ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Learning Techniques ◽  
Measurement Units ◽  
The Difference

The field of human activity recognition (HAR) often utilizes wearable sensors and machine learning techniques in order to identify the actions of the subject. This paper considers the activity recognition of walking and running while using a support vector machine (SVM) that was trained on principal components derived from wearable sensor data. An ablation analysis is performed in order to select the subset of sensors that yield the highest classification accuracy. The paper also compares principal components across trials to inform the similarity of the trials. Five subjects were instructed to perform standing, walking, running, and sprinting on a self-paced treadmill, and the data were recorded while using surface electromyography sensors (sEMGs), inertial measurement units (IMUs), and force plates. When all of the sensors were included, the SVM had over 90% classification accuracy using only the first three principal components of the data with the classes of stand, walk, and run/sprint (combined run and sprint class). It was found that sensors that were placed only on the lower leg produce higher accuracies than sensors placed on the upper leg. There was a small decrease in accuracy when the force plates are ablated, but the difference may not be operationally relevant. Using only accelerometers without sEMGs was shown to decrease the accuracy of the SVM.

Sign in / Sign up

Export Citation Format

Share Document