Techniques for Machine Learning based Spatial Data Analysis: Research Directions

Gangappa, M.; Kiran, C.; Sammulal, P.

doi:10.5120/ijca2017914643

Cited by 6 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The important thing of this paradigm is the unconventional structure of the information processing systems. They can give reasonable answers for issues, which are for the most part described by non-linear ties, high dimensional, noisy, complex, loose, and imperfect or mistake inclined sensor information [20]. Similar to biological neural networks, it is a system composed of many interconnected neurons (nerve cells), which receive process and transfer information.…”

Section: Artificial Neural Network In Context Of Spatial Data Miningmentioning

confidence: 99%

New approaches to processing GIS Data using Artificial Neural Networks models

Mihai

2021

AUCMCS

View full text Add to dashboard Cite

Spatial data mining is a special type of data mining. The main difference between data mining and spatial data mining is that in spatial data mining tasks we use not only non-spatial attributes but also spatial attributes. Spatial data mining techniques have strong relationship with GIS (Geographical Information System) and are widely used in GIS for inferring association among spatial attributes, clustering and classifying information with respect to spatial attributes. In this paper we use the statistical package Weka on two models, which consist of two parcels plans from the Olt area of Romania. In our experimentation, we compare the results of the vector models depending on the values of the training datasets. Using these models with GIS data from the domain of Cadaster we analyze the performance of the Artificial Neural Networks in context of spatial data mining.

show abstract

Section: Artificial Neural Network In Context Of Spatial Data Miningmentioning

confidence: 99%

New approaches to processing GIS Data using Artificial Neural Networks models

Mihai

2021

AUCMCS

View full text Add to dashboard Cite

show abstract

“…Supervised ML algorithms can be trained using data to create a model for the prediction of specific phenomena [24]. For example, Generalized Linear Models (GLM) and Generalized Additive Models (GAM) were reported by [13] and [25], respectively, where improved landslide susceptibility modelling was obtained by taking advantage of the linear and nonlinear relationships of the predictor variables.…”

Section: Related Studiesmentioning

confidence: 99%

Landslide Susceptibility Mapping: Machine and Ensemble Learning Based on Remote Sensing Big Data

Kalantar

Ueda

Saeidi³

et al. 2020

Remote Sensing

111

View full text Add to dashboard Cite

Predicting landslide occurrences can be difficult. However, failure to do so can be catastrophic, causing unwanted tragedies such as property damage, community displacement, and human casualties. Research into landslide susceptibility mapping (LSM) attempts to alleviate such catastrophes through the identification of landslide prone areas. Computational modelling techniques have been successful in related disaster scenarios, which motivate this work to explore such modelling for LSM. In this research, the potential of supervised machine learning and ensemble learning is investigated. Firstly, the Flexible Discriminant Analysis (FDA) supervised learning algorithm is trained for LSM and compared against other algorithms that have been widely used for the same purpose, namely Generalized Logistic Models (GLM), Boosted Regression Trees (BRT or GBM), and Random Forest (RF). Next, an ensemble model consisting of all four algorithms is implemented to examine possible performance improvements. The dataset used to train and test all the algorithms consists of a landslide inventory map of 227 landslide locations. From these sources, 13 conditioning factors are extracted to be used in the models. Experimental evaluations are made based on True Skill Statistic (TSS), the Receiver Operation characteristic (ROC) curve and kappa index. The results show that the best TSS (0.6986), ROC (0.904) and kappa (0.6915) were obtained by the ensemble model. FDA on its own seems effective at modelling landslide susceptibility from multiple data sources, with performance comparable to GLM. However, it slightly underperforms when compared to GBM (BRT) and RF. RF seems most capable compared to GBM, GLM, and FDA, when dealing with all conditioning factors.

show abstract

“…Shirzadi et al research [22] has also demonstrated that less complex ML can still be used in a variety of applications despite the deep learning trend. Data can be used to train supervised ML algorithms to build models for the prediction of particular phenomena [38] as described by [39]. In another study [40], In addition to random forest and CART, boosted regression tree (BRT) and GLM were employed to identify areas at risk for landslides (classification and regression tree).…”

Section: Introductionmentioning

confidence: 99%

Weight Optimization for missing data prediction of Landslide Susceptibility Mapping in Remote sensing Analysis

et al. 2024

JMC

View full text Add to dashboard Cite

To keep track of changes to the Earth's surface, extensive time series of data from remote sensing using image processing is required. This research is motivated by the effectiveness of computational modelling techniques; however, the problem of missing data is multifaceted. When data at numerous a-periodic timestamps are absent during multi-temporal analysis, the issue becomes increasingly problematic. To make remote sensing time series analysis easier, weight optimised machine learning is used in this study to rebuild lost data. Keeping the causality restriction in mind, this method makes use of data from previous and subsequent timestamps. The architecture is based on an ensemble of numerous forecasting modules, built on the observed data in the time-series order. Dummy data is used to connect the forecasting modules, which were previously linked by the earlier half of the sequence. After that, iterative improvements are made to the dummy data to make it better fit the next segment of the sequence. On the basis of Landsat-7 TM-5 satellite imagery, the work has been proven to be accurate in forecasting missing images in normalised difference vegetation index time series. In a performance evaluation, the proposed forecasting model was shown to be effective.

show abstract

Techniques for Machine Learning based Spatial Data Analysis: Research Directions

Cited by 6 publications

References 10 publications

New approaches to processing GIS Data using Artificial Neural Networks models

New approaches to processing GIS Data using Artificial Neural Networks models

Landslide Susceptibility Mapping: Machine and Ensemble Learning Based on Remote Sensing Big Data

Weight Optimization for missing data prediction of Landslide Susceptibility Mapping in Remote sensing Analysis

Contact Info

Product

Resources

About