High-quality Training Samples Research Articles

Mapping corn dynamics using limited but representative samples with adaptive strategies

Mapping the corn dynamics at a large scale and multiple years is essential for global food security. Traditional mapping approaches by collecting training samples from field surveys are labor-intensive, challenging large-scale mapping of corn dynamics over the long term. This study developed an efficient approach to map large-scale corn dynamics in the main corn districts of the United States (US) using adaptive strategies for collecting high-quality training samples. First, this study proposed an automatic approach to collect stable and representative corn samples from the crop data layers (CDL) product. Then, this study improved the mapping performance of corn at a large scale and in earlier years by using adaptive strategies to collect limited (less than 500) but high-quality training samples. Finally, this study assessed and discussed the model performance across spaces and years using multi-source datasets from 2001 to 2020. Our results indicate the proposed approach with adaptive strategies can generate robust classification models with good performance in mapping large-scale corn dynamics. In our study area, the mean overall accuracy (OA) of corn is about 88% if using the CDL data as a reference. Besides, the R2 of corn areas at the county scale between our result and the surveyed acreage statistics is above 0.9, suggesting the proposed strategy is helpful for mapping corn dynamics across different years. The proposed approach demonstrated that limited but representative samples could map corn dynamics at a large scale with good performance, showing significant improvement compared to the traditional approach. It is feasible to map crop dynamics with multiple types by combining existing crop products with collected field samples, particularly in China, where crop products at the national scale are still lacking.

Low-quality training data detection method of EEG signals for motor imagery BCI system

BackgroundThe design and implementation of high-performance motor imagery-based brain computer interface (MI-BCI) requires high-quality training samples. However, fluctuation in subjects’ physiological and mental states as well as artifacts can produce the low-quality motor imagery electroencephalogram (EEG) signal, which will damage the performance of MI-BCI system. New methodIn order to select high-quality MI-EEG training data, this paper proposes a low-quality training data detection method combining independent component analysis (ICA) and weak classifier cluster. we also design and implement a new online BCI system based on motor imagery to verify the online processing performance of the proposed method. ResultIn order to verify the effectiveness of the proposed method, we conducted offline experiments on the public dataset called BCI Competition IV Data Set 2b. Furthermore, in order to verify the processing performance of the online system, we designed 60 groups of online experiments on 12 subjects. The online experimental results show that the twelve subjects can complete the system task efficiently (the best experiment is 135.6 s with 9 trials of subject S1). ConclusionThis paper demonstrated that the proposed low-quality training data detection method can effectively screen out low-quality training samples, so as to improve the performance of the MI-BCI system.

Reprint of: Few-shot learning for cardiac arrhythmia detection based on electrocardiogram data from wearable devices

Wearable devices have dramatically developed over the past decade as their functions extended from the simple posture analysis to non-invasive condition monitoring for early warning and proactive healthcare, which are especially significant for the dangerous disease such as cardiac arrhythmia. However, it is difficult for the wearable devices to collect plentiful and high-quality training samples so as to meet the fundamental requirements for the learning-based methods. To address this challenge, we propose a meta-transfer based few-shot learning method to handle arrhythmia classification with the ECG signal from the wearable devices. First, the original ECG signals are converted into spectrograms applicable to the 2D-CNN models. Second, we propose the special large-training scheme to pre-train the feature extractor to emphasize the meaningful information for classification, and the feature output dimension is reshaped to reduce the influence of irrelevant and redundant information. Then, the meta-transfer scheme is developed to avoid the training from scratch, which is prone to overfitting without the adequate samples. Finally, we conduct the extensive experiments to assess the performance of our method. The experimental results illustrate that the proposed method outperforms in accuracy than other comparative methods when handling the various few-shot tasks under the same training samples.

Injecting spectral indices to transferable convolutional neural network under imbalanced and noisy labels for Landsat image classification

ABSTRACT Stable and continuous remote sensing land-cover mapping is important for agriculture, ecosystems, and land management. Convolutional neural networks (CNNs) are promising methods for achieving this goal. However, the large number of high-quality training samples required to train a CNN is difficult to acquire. In practice, imbalanced and noisy labels originating from existing land-cover maps can be used as alternatives. Experiments have shown that the inconsistency in the training samples has a significant impact on the performance of the CNN. To overcome this drawback, a method is proposed to inject highly consistent information into the network, to learn general and transferable features to alleviate the impact of imperfect training samples. Spectral indices are important features that can provide consistent information. These indices can be fused with CNN feature maps which utilize information entropy to choose the most appropriate CNN layer, to compensate for the inconsistency caused by the imbalanced, noisy labels. The proposed transferable CNN, tested with imbalanced and noisy labels for inter-regional Landsat time-series, not only is superior in terms of accuracy for land-cover mapping but also demonstrates excellent transferability between regions in both time series and cross-regional Landsat image classification.

NeuCrowd: neural sampling network for representation learning with crowdsourced labels

Representation learning approaches require a massive amount of discriminative training data, which is unavailable in many scenarios, such as healthcare, smart city, and education. In practice, people refer to crowdsourcing to get annotated labels. However, due to issues like data privacy, budget limitation, shortage of domain-specific annotators, the number of crowdsourced labels is still very limited. Moreover, because of annotators’ diverse expertise, crowdsourced labels are often inconsistent. Thus, directly applying existing supervised representation learning (SRL) algorithms may easily get the overfitting problem and yield suboptimal solutions. In this paper, we propose NeuCrowd, a unified framework for SRL from crowdsourced labels. The proposed framework (1) creates a sufficient number of high-quality n-tuplet training samples by utilizing safety-aware sampling and robust anchor generation; and (2) automatically learns a neural sampling network that adaptively learns to select effective samples for SRL networks. The proposed framework is evaluated on both one synthetic and three real-world data sets. The results show that our approach outperforms a wide range of state-of-the-art baselines in terms of prediction accuracy and AUC. To encourage reproducible results, we make our code publicly available at https://github.com/tal-ai/NeuCrowd_KAIS2021 .

Selective transfer learning with adversarial training for stock movement prediction

Stock movement prediction is a critical issue in the field of financial investment. It is very challenging since a stock usually shows highly stochastic property in price and has complex relationships with other stocks. Most existing approaches cannot jointly take the above two issues into account and thus cannot yield satisfactory prediction result. This paper contributes a new stock movement prediction model, Selective Transfer Learning with Adversarial Training (STLAT). Our STLAT method advances existing solutions in two major aspects: (i) tailoring the pre-trained and fine-tuned method for stock movement prediction and (ii) introducing the data selector module to select the more relevant training samples. More specifically, we pre-train the shared base model using three different tasks. The predictor task is constructed to measure the performance of the shared base model with source domain data and target domain data. The adversarial training task is constructed to improve the generalisation of the shared base model. The data selector task is introduced to select the most relevant and high-quality training samples from stocks in source domain. All three tasks are jointly trained with a loss function. As a result, the pre-trained shared base model can be fine-tuned with the stock data in target domain. To validate our method, we perform the back-testing on the historical data of two public datasets and a newly constructed dataset. Extensive experiments demonstrate the superiority of our STLAT method. It outperforms state-of-the-art stock prediction solutions on ACC evaluation of 3.76%, 4.12%, 4.89% on ACL18, KDD17 and CN50, respectively.

REL-SAGAN: Relative Generation Adversarial Network Integrated With Attention Mechanism for Scene Data Augmentation of Remote Sensing

Deep learning shows a strong ability in target detection, scene classification, and change detection of remote sensing. However, the training process requires a large number of samples, and the production of most high-quality training samples requires a lot of time and human resources. With the resolution of remote sensing image gradually improved, and the scene information becoming more and more complicated, the sample augmentation methods at this stage have shown obvious defects, such as the loss of sample key information and the lack of diversity in augmented data sets. In order to solve these problems, this article proposes a new augmentation method for remote sensing scene data named Rel-SAGAN based on generative adversarial networks (GAN). First, combined with self-attention mechanism to improve the large-scale feature learning ability and reduce the calculation parameters of GAN. Second, using relativity adversarial loss function to improve the structural stability of GAN. Furthermore, increasing convolution kernel and deeper structural of GAN to improve the ability of global feature extraction and saving the training time. Finally, taking NWPU remote sensing image dataset as experimental data, the effectiveness of the method proposed in this article is verified through ResNet-18. The experimental results show that it can generate more diverse high-resolution remote sensing natural scene images, the overall classification accuracy of augmented training dataset of remote sensing used high-quality generated images selected based on inception score and Frechet inception distance evaluations is improved by more than 3% and the classification accuracy is generally higher than the traditional data augmentation methods.

Improving the Accuracy of Land Cover Mapping by Distributing Training Samples

High-quality training samples are essential for accurate land cover classification. Due to the difficulties in collecting a large number of training samples, it is of great significance to collect a high-quality sample dataset with a limited sample size but effective sample distribution. In this paper, we proposed an object-oriented sampling approach by segmenting image blocks expanded from systematically distributed seeds (object-oriented sampling approach) and carried out a rigorous comparison of seven sampling strategies, including random sampling, systematic sampling, stratified sampling (stratified sampling with the strata of land cover classes based on classification product, Latin hypercube sampling, and spatial Latin hypercube sampling), object-oriented sampling, and manual sampling, to explore the impact of training sample distribution on the accuracy of land cover classification when the samples are limited. Five study areas from different climate zones were selected along the China–Mongolia border. Our research identified the proposed object-oriented sampling approach as the first-choice sampling strategy in collecting training samples. This approach improved the diversity and completeness of the training sample set. Stratified sampling with strata defined by the combination of different attributes and stratified sampling with the strata of land cover classes had their limitations, and they performed well in specific situations when we have enough prior knowledge or high-accuracy product. Manual sampling was greatly influenced by the experience of interpreters. All these sampling strategies mentioned above outperformed random sampling and systematic sampling in this study. The results indicate that the sampling strategies of training datasets do have great impacts on the land cover classification accuracies when the sample size is limited. This paper will provide guidance for efficient training sample collection to increase classification accuracies.

Research and application of bolt defects detection technology based on machine learning

With the development of computer technology, the technology based on computer machine learning plays an important role in various fields. Using drones for collecting image data and using machine learning to analyze the collected image data have become the current general method of intelligent detection technology. As the main machine learning method, deep learning is commonly used in image analysis, but it requires many high-quality training samples and high-performance embedded system. In the engineering quality and safety detection with few training samples, the detection effect of this method is not satisfactory. To solve this problem, computer vision and machine learning technology are introduced into image analysis of bolt, based on the analysis and mining of historical image samples, the recognition and judgment of new collected images can be realized by matching the newly collected image samples and historical samples. Taking the bolt on a steel structure bridge as an example, this method is used to recognize the bolt appearance image collected by UAV. The results show that the method can effectively identify the appearance state of bolts, with fast calculation speed and high recognition accuracy.

CCT: Conditional Co-Training for Truly Unsupervised Remote Sensing Image Segmentation in Coastal Areas

As the fastest growing trend in big data analysis, deep learning technology has proven to be both an unprecedented breakthrough and a powerful tool in many fields, particularly for image segmentation tasks. Nevertheless, most achievements depend on high-quality pre-labeled training samples, which are labor-intensive and time-consuming. Furthermore, different from conventional natural images, coastal remote sensing ones generally carry far more complicated and considerable land cover information, making it difficult to produce pre-labeled references for supervised image segmentation. In our research, motivated by this observation, we take an in-depth investigation on the utilization of neural networks for unsupervised learning and propose a novel method, namely conditional co-training (CCT), specifically for truly unsupervised remote sensing image segmentation in coastal areas. In our idea, a multi-model framework consisting of two parallel data streams, which are superpixel-based over-segmentation and pixel-level semantic segmentation, is proposed to simultaneously perform the pixel-level classification. The former processes the input image into multiple over-segments, providing self-constrained guidance for model training. Meanwhile, with this guidance, the latter continuously processes the input image into multi-channel response maps until the model converges. Incentivized by multiple conditional constraints, our framework learns to extract high-level semantic knowledge and produce full-resolution segmentation maps without pre-labeled ground truths. Compared to the black-box solutions in conventional supervised learning manners, this method is of stronger explainability and transparency for its specific architecture and mechanism. The experimental results on two representative real-world coastal remote sensing datasets of image segmentation and the comparison with other state-of-the-art truly unsupervised methods validate the plausible performance and excellent efficiency of our proposed CCT.

Structural pixel-wise target attention for robust object tracking

Some Siamese-based trackers use temporal context prior as structural constraint to suppress background distractors. However, due to the lack of contour recognition, it is difficult to obtain a better performance. In order to address this issue, we propose a structural pixel-wise target attention strategy for robust object tracking with memory model. Firstly, a pixel-wise target attention model is constructed for evaluating the probability that the pixel belongs to the target, which can effectively discriminate the target boundary so as to highlight the target area. Meanwhile, structural information is used to solve pixel-wise distractors, which is combined with complementary pixel-wise label constraints to obtain a structural pixel-wise target attention model. This attention mechanism can improve the confidence of the final response map and achieve more reliable target location. Secondly, a memory model is learned using the highly reliable memory pattern for providing high-quality training samples for updating pixel-wise target attention model. Benefiting from this method, our method realizes the pixel-wise target attention model to adapt to the variation of the target while preventing the background noise, thus improving the discriminability of the model. Finally, the structural pixel-wise target attention mechanism and memory model are integrated into the Siamese-based tracking framework, which shows better merit for robust object tracking. Extensive experiments on multiple tracking benchmarks show that our approach achieves excellent performance in various challenging target tracking tasks.

Hbox {CDBTune}^{+}: An efficient deep reinforcement learning-based automatic cloud database tuning system

Configuration tuning is vital to optimize the performance of a database management system (DBMS). It becomes more tedious and urgent for cloud databases (CDB) due to diverse database instances and query workloads, which make the job of a database administrator (DBA) very difficult. Existing solutions for automatic DBMS configuration tuning have several limitations. Firstly, they adopt a pipelined learning model but cannot optimize the overall performance in an end-to-end manner. Secondly, they rely on large-scale high-quality training samples which are hard to obtain. Thirdly, existing approaches cannot recommend reasonable configurations for a large number of knobs to tune whose potential values live in such high-dimensional continuous space. Lastly, in cloud environments, existing approaches can hardly cope with the changes of hardware configurations and workloads, and have poor adaptability. To address these challenges, we design an end-to-end automatic CDB tuning system, {texttt {CDBTune}}^{+}, using deep reinforcement learning (RL). {texttt {CDBTune}}^{+} utilizes the deep deterministic policy gradient method to find the optimal configurations in a high-dimensional continuous space. {texttt {CDBTune}}^{+} adopts a trial-and-error strategy to learn knob settings with a limited number of samples to accomplish the initial training, which alleviates the necessity of collecting a massive amount of high-quality samples. {texttt {CDBTune}}^{+} adopts the reward-feedback mechanism in RL instead of traditional regression, which enables end-to-end learning and accelerates the convergence speed of our model and improves the efficiency of online tuning. Besides, we propose effective techniques to improve the training and tuning efficiency of {texttt {CDBTune}}^{+} for practical usage in a cloud environment. We conducted extensive experiments under 7 different workloads on real cloud databases to evaluate {texttt {CDBTune}}^{+}. Experimental results showed that {texttt {CDBTune}}^{+} adapts well to a new hardware environment or workload, and significantly outperformed the state-of-the-art tuning tools and DBA experts.

Few-shot learning for cardiac arrhythmia detection based on electrocardiogram data from wearable devices

Wearable devices have dramatically developed over the past decade as their functions extended from the simple posture analysis to non-invasive condition monitoring for early warning and proactive healthcare, which are especially significant for the dangerous disease such as cardiac arrhythmia. However, it is difficult for the wearable devices to collect plentiful and high-quality training samples so as to meet the fundamental requirements for the learning-based methods. To address this challenge, we propose a meta-transfer based few-shot learning method to handle arrhythmia classification with the ECG signal from the wearable devices. First, the original ECG signals are converted into spectrograms applicable to the 2D-CNN models. Second, we propose the special large-training scheme to pre-train the feature extractor to emphasize the meaningful information for classification, and the feature output dimension is reshaped to reduce the influence of irrelevant and redundant information. Then, the meta-transfer scheme is developed to avoid the training from scratch, which is prone to overfitting without the adequate samples. Finally, we conduct the extensive experiments to assess the performance of our method. The experimental results illustrate that the proposed method outperforms in accuracy than other comparative methods when handling the various few-shot tasks under the same training samples.

Mapping the Technological Landscape of Emerging Industry Value Chain Through a Patent Lens: An Integrated Framework With Deep Learning

Recent research applies patent autoclassification using machine learning to map the technological landscape of an industry value chain. However, when these methods are applied to emerging industries, the available patent sample data are small-scale and unevenly distributed, which cause overfitting and reduce the accuracy of patent classification. Therefore, this article proposes a framework to map the technological landscape of an emerging industry value chain through patent analysis with deep learning, which integrates a generative adversarial network as a data-augmentation method to overcome the problem of low-quality emerging-industry patent samples, and a deep neural network as a patent classifier. Based on this framework, this article conducts an application case of the 3-D printing industry. The evaluation results show that the integrated framework can effectively classify the patents with small-scale and unevenly distributed sample data, and depict the technological landscape of an emerging industry value chain. This article develops an efficient, reliable framework for patent autoclassification of emerging industries to overcome the lack of high-quality training samples, and it sheds light on the emerging industry value chain analysis with deep learning.

An Improved CNN-Based Apple Appearance Quality Classification Method With Small Samples

Apple quality classification is an important means to refine apple sales market and promote apple sales. At present, most of classification methods based on a convolutional neural network (CNN) depend on the quantity of training samples to get good performance. But due to the lack of large-scale public apple appearance dataset, it is a big challenge to obtain high accuracy of apple appearance quality classification with small samples. Therefore, we propose an improved method based on CNN for apple appearance, quality classification with small samples. Firstly, support vector machine (SVM) is used for image segmentation to avoid the decrease of recognition accuracy caused by environmental noise. Secondly, the segmented image data are input into deep convolutional generative adversarial networks (DCGAN) model, which is used for data expansion. Thirdly, the improved ResNet50 (Imp-ResNet50) is proposed as follows: Replace the fully-connected layer with global average pooling layer; Add the dropout algorithm and batch normalization algorithm at the fully-connected layer; Replace the activation function ReLU with Swish. Through comparative experiments with 360 apple images, we verify the performance of the proposed method including the training image quality, the running time, and classification accuracy. The result shows that the proposed method can obtain high quality training samples and reduce the running time of the method effectively. At the same time, it can realize higher classification accuracy that is up to 96.5%, which is higher than the previous classification method.

Model-Based Synthetic Geoelectric Sampling for Magnetotelluric Inversion With Deep Neural Networks

Neural networks (NNs) are efficient tools for rapidly obtaining geoelectric models to solve magnetotelluric (MT) inversion problems. Training an NN with strong predictive power requires numerous training samples to prevent underfitting. To reduce the computational burden of generating a large number of training samples, this work analyzes the influence of the sample features and distribution on the training effect for an NN and proposes an efficient method of sample generation. This innovative method consists of three steps: 1) geoelectrically simplifying the features; 2) removing unnecessary features on the basis of realistic geological characteristics; and 3) mapping the samples to a higher-dimensional space. Numerical examples based on simple stratified models show that the number of samples can be reduced to below one-millionth of the original number while improving the predictive effect of the NN. The performance and effectiveness for processing more complex structures are verified by the inversion results obtained for a public data set, COPROD2. We conclude that this advanced method can generate high-quality training samples at a greatly reduced computational cost. The analysis of the sample features and distribution not only advances the state of research on the use of machine learning in geophysical inversion but also is a forward-looking study on the mechanisms of underfitting, tracing the source of these phenomena back to the training samples used.

Combining Graph-Based Learning With Automated Data Collection for Code Vulnerability Detection

This paper presents FUNDED (Flow-sensitive vUl-Nerability coDE Detection), a novel learning framework for building vulnerability detection models. Funded leverages the advances in graph neural networks (GNNs) to develop a novel graph-based learning method to capture and reason about the program's control, data, and call dependencies. Unlike prior work that treats the program as a sequential sequence or an untyped graph, Funded learns and operates on a graph representation of the program source code, in which individual statements are connected to other statements through relational edges. By capturing the program syntax, semantics and flows, Funded finds better code representation for the downstream software vulnerability detection task. To provide sufficient training data to build an effective deep learning model, we combine probabilistic learning and statistical assessments to automatically gather high-quality training samples from open-source projects. This provides many real-life vulnerable code training samples to complement the limited vulnerable code samples available in standard vulnerability databases. We apply Funded to identify software vulnerabilities at the function level from program source code. We evaluate Funded on large real-world datasets with programs written in C, Java, Swift and Php, and compare it against six state-of-the-art code vulnerability detection models. Experimental results show that Funded significantly outperforms alternative approaches across evaluation settings.

TAILORED FEATURES FOR SEMANTIC SEGMENTATION WITH A DGCNN USING FREE TRAINING SAMPLES OF A COLORED AIRBORNE POINT CLOUD

Abstract. Automation of 3D LiDAR point cloud processing is expected to increase the production rate of many applications including automatic map generation. Fast development on high-end hardware has boosted the expansion of deep learning research for 3D classification and segmentation. However, deep learning requires large amount of high quality training samples. The generation of training samples for accurate classification results, especially for airborne point cloud data, is still problematic. Moreover, which customized features should be used best for segmenting airborne point cloud data is still unclear. This paper proposes semi-automatic point cloud labelling and examines the potential of combining different tailor-made features for pointwise semantic segmentation of an airborne point cloud. We implement a Dynamic Graph CNN (DGCNN) approach to classify airborne point cloud data into four land cover classes: bare-land, trees, buildings and roads. The DGCNN architecture is chosen as this network relates two approaches, PointNet and graph CNNs, to exploit the geometric relationships between points. For experiments, we train an airborne point cloud and co-aligned orthophoto of the Surabaya city area of Indonesia to DGCNN using three different tailor-made feature combinations: points with RGB (Red, Green, Blue) color, points with original LiDAR features (Intensity, Return number, Number of returns) so-called IRN, and points with two spectral colors and Intensity (Red, Green, Intensity) so-called RGI. The overall accuracy of the testing area indicates that using RGB information gives the best segmentation results of 81.05% while IRN and RGI gives accuracy values of 76.13%, and 79.81%, respectively.

A Coarse-to-Fine Deep Learning Based Land Use Change Detection Method for High-Resolution Remote Sensing Images

In recent decades, high-resolution (HR) remote sensing images have shown considerable potential for providing detailed information for change detection. The traditional change detection methods based on HR remote sensing images mostly only detect a single land type or only the change range, and cannot simultaneously detect the change of all object types and pixel-level range changes in the area. To overcome this difficulty, we propose a new coarse-to-fine deep learning-based land-use change detection method. We independently created a new scene classification dataset called NS-55, and innovatively considered the adaptation relationship between the convolutional neural network (CNN) and the scene complexity by selecting the CNN that best fit the scene complexity. The CNN trained by NS-55 was used to detect the category of the scene, define the final category of the scene according to the majority voting method, and obtain the changed scene by comparison to obtain the so-called coarse change result. Then, we created a multi-scale threshold (MST) method, which is a new method for obtaining high-quality training samples. We used the high-quality samples selected by MST to train the deep belief network to obtain the pixel-level range change detection results. By mapping coarse scene changes to range changes, we could obtain fine multi-type land-use change detection results. Experiments were conducted on the Multi-temporal Scene Wuhan dataset and aerial images of a particular area of Dapeng New District, Shenzhen, where promising results were achieved by the proposed method. This demonstrates that the proposed method is practical, easy-to-implement, and the NS-55 dataset is physically justified. The proposed method has the potential to be applied in the large scale land use fine change detection problem and qualitative and quantitative research on land use/cover change based on HR remote sensing data.

Using High Resolution Optical Imagery to Detect Earthquake-Induced Liquefaction: The 2011 Christchurch Earthquake

Using automated supervised methods with satellite and aerial imageries for liquefaction mapping is a promising step in providing detailed and region-scale maps of liquefaction extent immediately after an earthquake. The accuracy of these methods depends on the quantity and quality of training samples and the number of available spectral bands. Digitizing a large number of high-quality training samples from an event may not be feasible in the desired timeframe for rapid response as the training pixels for each class should be typical and accurately represent the spectral diversity of that specific class. To perform automated classification for liquefaction detection, we need to understand how to build the optimal and accurate training dataset. Using multispectral optical imagery from the 22 February, 2011 Christchurch earthquake, we investigate the effects of quantity of high-quality training pixel samples as well as the number of spectral bands on the performance of a pixel-based parametric supervised maximum likelihood classifier for liquefaction detection. We find that the liquefaction surface effects are bimodal in terms of spectral signature and therefore, should be classified as either wet liquefaction or dry liquefaction. This is due to the difference in water content between these two modes. Using 5-fold cross-validation method, we evaluate performance of the classifier on datasets with different pixel sizes of 50, 100, 500, 2000, and 4000. Also, the effect of adding spectral information was investigated by adding once only the near infrared (NIR) band to the visible red, green, and blue (RGB) bands and the other time using all available 8 spectral bands of the World-View 2 satellite imagery. We find that the classifier has high accuracies (75%–95%) when using the 2000 pixels-size dataset that includes the RGB+NIR spectral bands and therefore, increasing to 4000 pixels-size dataset and/or eight spectral bands may not be worth the required time and cost. We also investigate accuracies of the classifier when using aerial imagery with same number of training pixels and either RGB or RGB+NIR bands and find that the classifier accuracies are higher when using satellite imagery with same number of training pixels and spectral information. The classifier identifies dry liquefaction with higher user accuracy than wet liquefaction across all evaluated scenarios. To improve classification performance for wet liquefaction detection, we also investigate adding geospatial information of building footprints to improve classification performance. We find that using a building footprint mask to remove them from the classification process, increases wet liquefaction user accuracy by roughly 10%.