Multispectral multi-temporal crop cover classification over Türkiye using random forest algorithm

Download

index.pdf

Date

2022-7-28

Author

Dönmez Altındal, Elif

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

257
views

72
downloads

Accurate crop cover maps are beneficial for various aspects like water resources management, crop yield prediction, regulation insurance policies, and investigation of the effects of climate change. In this thesis, agricultural crop mapping is performed over Türkiye. Sentinel-2 Level-2A images with 10-meter spatial resolution acquired between March 15, 2019, and October 15, 2019, are reduced to 15-day median images. In addition to spectral bands, Normalized Difference Vegetation Index (NDVI) and Normalized Difference Water Index (NDWI) are used as classification features. Twenty years of ERA5-Land 2-meter temperature data is averaged to divide the study area into three temperature zones as Low (LTZ), Medium (MTZ), and High-Temperature Zones (HTZ). Before the classification, feature selection using random forest importance is performed to select the most successful features. After that, a random forest classifier is created for each temperature zone. LTZ reached 89% overall accuracy (OA) with a 0.88 Kappa. MTZ reached 91% OA with 0.92 Kappa, and HTZ reached 94% OA with 0.94 Kappa, giving the best accuracy among the classifiers. Finally, test sets of all temperature zones are combined, and OA of 92% with a Kappa of 0.93 is achieved with this combined test set. To test the advantage of temperature zoning, classification is also performed without the temperature zones, and it is observed that temperature zoning increases the OA and Kappa by 1%. A land cover classification map is then created using temperature zone classifiers with 34 crop classes and six non-agricultural classes.

Subject Keywords

Remote sensing, Crop cover mapping, Machine learning, Supervised classification

URI

https://hdl.handle.net/11511/98586

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

A data-driven approach for predicting solar energy potential of buildings in urban fabric Duran, Ayça; Gürsel Dino, İpek; Department of Architecture (2022-7) Energy-efficient buildings that use clean and sustainable energy sources are urgently needed to reduce the environmental impact of buildings and mitigate climate change in cities. Buildings have great potential in harvesting solar energy by their solar exposure capacity. Developments in PV technologies also encourage the integration of PV systems into architectural applications. However, urban contexts can limit solar energy generation capacity of buildings by shading building envelopes and reducing availab...
Evaluating land use/cover change with temporal satellite data and information systems Erener, Arzu; Duzgun, Sebnem; Yalçıner, Ahmet Cevdet (2012-01-01) Rapid changes in land use land cover (LULC) adversely affect the environment. In order to provide information for policymakers to support sustainable development, detailed data about these regions is urgently needed. Use of remote sensing (RS) in combination with geographical information System (GIS) is one of the effective information technology tools to generate LULC change information. In this study, it is aimed to explore the temporal and spatial characteristics of urban expansion by using RS integrated...
A BIM-based building circularity framework: assessment and visualization through 5R strategies Yüksel, Pınar Ece; Atasoy Özcan, Güzide; Department of Civil Engineering (2023-1-26) Principles of the circular economy are applied to improve resource efficiency and reduce environmental impact. The purpose of this thesis is to create a BIM-based framework for building circularity assessment (BCA) that enables an analysis of R strategies such as Reusing, Recycling and Rethinking with graphically aided data representation and supports decision-making starting from the early stages to end of life. To learn more about building circularity indicators and assessment approaches, a literature rev...
Superensembles of raw and bias-adjusted regional climate models for Mediterranean region, Turkey Mesta, Buket; Kentel Erdoğan, Elçin (2021-09-01) For regional-scale studies on climate change and relevant impact assessment, the projections of regional climate models (RCMs) are used due to their advantage of high resolution and better representation of the local climate relative to the global climate models. However, direct use of RCM outputs is prone to uncertainties and biases that may significantly diminish the accuracy of results. EURO-COordinated Regional Downscaling EXperiment (CORDEX) initiative that is a part of the global Coordinated Regional ...
Comparison of BEST and LEED green building rating systems through cost based optimization Uğurlu, Bengisu; Aksoy, Ayşegül; Department of Environmental Engineering (2020-1-25) Buildings have significant effects on climate change due to vast resource consumption and pollution generation. Improving the effective use of limited resources and constructing environmentally friendly buildings are important in the realm of mitigations for climate change. Several countries have their green building rating systems tailored towards their regulations, distinctive climatic conditions, unique cultures and traditions, diverse building types and ages, or wide-ranging environmental, economic, and...

Citation Formats

E. Dönmez Altındal, “Multispectral multi-temporal crop cover classification over Türkiye using random forest algorithm,” M.S. - Master of Science, Middle East Technical University, 2022.