Comparison of Object Based Machine Learning Classifications of Planetscope and Worldview-3 Satellite Images for Land Use / Cover

Tuzcu, Aylin; Taşkın, Gülşen; Musaoğlu, Nebiye

doi:10.5194/isprs-archives-xlii-2-w13-1887-2019

Cited by 7 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jamali [14] aim to evaluate eight machine learning algorithms for image classification implemented in WEKA and R programming language. The aim of [15] was to compare performance of the classification methods, that are Rule Based classifier and Support Vector Machine, of Planetscope and Worldview-3 satellite images in order to produce land use/cover thematic maps. Six machine-learning algorithms, namely random forest, support vector machine, artificial neural network, fuzzy adaptive resonance theory-supervised predictive mapping, spectral angle mapper and Mahalanobis distance were examined in [3].…”

Section: Introductionmentioning

confidence: 99%

Using Landsat-5 for Accurate Historical LULC Classification: A Comparison of Machine Learning Models

Krivoguz,

Chernyi,

Zinchenko

et al. 2023

Data

View full text Add to dashboard Cite

This study investigates the application of various machine learning models for land use and land cover (LULC) classification in the Kerch Peninsula. The study utilizes archival field data, cadastral data, and published scientific literature for model training and testing, using Landsat-5 imagery from 1990 as input data. Four machine learning models (deep neural network, Random Forest, support vector machine (SVM), and AdaBoost) are employed, and their hyperparameters are tuned using random search and grid search. Model performance is evaluated through cross-validation and confusion matrices. The deep neural network achieves the highest accuracy (96.2%) and performs well in classifying water, urban lands, open soils, and high vegetation. However, it faces challenges in classifying grasslands, bare lands, and agricultural areas. The Random Forest model achieves an accuracy of 90.5% but struggles with differentiating high vegetation from agricultural lands. The SVM model achieves an accuracy of 86.1%, while the AdaBoost model performs the lowest with an accuracy of 58.4%. The novel contributions of this study include the comparison and evaluation of multiple machine learning models for land use classification in the Kerch Peninsula. The deep neural network and Random Forest models outperform SVM and AdaBoost in terms of accuracy. However, the use of limited data sources such as cadastral data and scientific articles may introduce limitations and potential errors. Future research should consider incorporating field studies and additional data sources for improved accuracy. This study provides valuable insights for land use classification, facilitating the assessment and management of natural resources in the Kerch Peninsula. The findings contribute to informed decision-making processes and lay the groundwork for further research in the field.

show abstract

Section: Introductionmentioning

confidence: 99%

Using Landsat-5 for Accurate Historical LULC Classification: A Comparison of Machine Learning Models

Krivoguz,

Chernyi,

Zinchenko

et al. 2023

Data

View full text Add to dashboard Cite

show abstract

“…Comparatively, WorldView-2 has better spatial resolution and clearer display on object, rather than PlanetScope which has generalized visualization of object so that hypothetically it could provide better textureal information. Previous research has been conducted to compare the results between PlanetScope and WorldView with the highest result coming from WorldView imagery [3,4]. However, this research only asess the accuracy results of the land use mapping on general classes such as builtup, vegetation, bareland, etc., not the specific classes on residential based on socioeconomic aspect.…”

Section: Introductionmentioning

confidence: 99%

Comparing WorldView-2 and PlanetScope Imagery to Mapping Housing Types Using GEOBIA

Hafiudzan,

Widayani,

Rahardjo

2023

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

The mapping accuracy of housing types plays a vital role in urban planning and development. Choosing the right imagery for urban geospatial analysis matters in terms of spatial or textural resolution. Here we compare the effectiveness of different satellite imagery, namely WorldView-2 (2m resolution) and PlanetScope (3m resolution) to map housing types. The segmentation algorithm employed is SNIC (Simple Non-Iterative Clustering) while SVM (Support Vector Machine) algorithm is for classification. This study assessed the performance of these satellite platforms in capturing to extract spatial and spectral elements of each housing class and differentiating between urban villages (Kampung Kota), government-based housing, and private-based gated housing classes in the Tangerang area. WorldView-2, with its high spatial resolution, provides detailed information, allowing for precise delineation of housing boundaries and distinctive features, whereas Planetscope imagery offers better textural information for the segmentation stage. Despite the coarser details, the SVM classification algorithm achieved an overall accuracy of 65.00% using PlanetScope imagery. Comparative analysis revealed that WorldView-2 imagery outperformed PlanetScope imagery in terms of overall accuracy, with an overall accuracy of 65.52%. The higher spatial resolution of WorldView-2 enables better discrimination of housing types, resulting in more accurate classification. However, PlanetScope imagery provides valuable information, particularly for large-scale urban planning applications. The findings of this study contribute to the field of remote sensing and assist urban planners in making informed decisions regarding housing development and infrastructure planning based on available satellite imagery resources, both of which have their own advantages and disadvantages.

show abstract

“…[18] used PS data with other satellite data to monitor crop growth. [19] used ML-based classification to make landuse maps based on PS data and observed an accuracy between 87% and 96%. [20] used PS data to analyze vegetation phenology in Kenya and advocated that the PS images have more detailed NDVI observations due to high spatiotemporal resolution.…”

Section: Introductionmentioning

confidence: 99%

Planetscope Nanosatellites Image Classification Using Machine Learning

Haq¹

2022

Computer Systems Science and Engineering

View full text Add to dashboard Cite

To adopt sustainable crop practices in changing climate, understanding the climatic parameters and water requirements with vegetation is crucial on a spatiotemporal scale. The Planetscope (PS) constellation of more than 130 nanosatellites from Planet Labs revolutionize the high-resolution vegetation assessment. PS-derived Normalized Difference Vegetation Index (NDVI) maps are one of the highest resolution data that can transform agricultural practices and management on a large scale. High-resolution PS nanosatellite data was utilized in the current study to monitor agriculture's spatiotemporal assessment for the Al-Qassim region, Kingdom of Saudi Arabia (KSA). The time series of NDVI was utilized to assess the vegetation pattern change in the study area. The current study area has sparse vegetation, and exposed soil exhibits brightness due to low soil moisture, constraining NDVI. Therefore, a machine learning (ML) based Random Forest (RF) classification model was used to compare the vegetation extent and computational cost of NDVI. The RF model has been compared with NDVI in the current investigation. It is one of the most precise classification methods because it can model the complexity of input variables, handle outliers, treat noise effectively, and avoid overfitting. Multinomial Logistic Regression (MLR) was implemented to compare the performance of both NDVI and RFbased classification. RF model provided good accuracy (98%) for all vegetation classes based on user accuracy, producer accuracy, and kappa coefficient.

show abstract

Comparison of Object Based Machine Learning Classifications of Planetscope and Worldview-3 Satellite Images for Land Use / Cover

Cited by 7 publications

References 18 publications

Using Landsat-5 for Accurate Historical LULC Classification: A Comparison of Machine Learning Models

Using Landsat-5 for Accurate Historical LULC Classification: A Comparison of Machine Learning Models

Comparing WorldView-2 and PlanetScope Imagery to Mapping Housing Types Using GEOBIA

Planetscope Nanosatellites Image Classification Using Machine Learning

Contact Info

Product

Resources

About