Early yield estimation by photosynthetic pigment abundances using landsat 8 image series

Özcan, Ayşenur
Timely estimation of crop yields is critical for monitoring global food production by international organizations as well as governments, farmers and the private sector dealing with storage, import and export of crops and associated products. Satellite remote sensing has the capability to provide near real-time information on a global scale. Combining satellite data and soft computing techniques to predict crop yields is a very effective strategy for continually forecasting crop yields. This thesis presents a novel approach for accurate and sustainable estimation of crop yields based on estimated abundances of endmembers that may be attributed to photosynthetic pigments. Landsat 8 images acquired during the time of the phenological cycle when plants have maximum greenness are the inputs to find endmembers and abundances within the pure wheat crop pixels using Robust Collaborative Nonnegative Matrix Factorization (R-CoNMF) unmixing algorithm. The endmembers are optimized to maximize the predictive power of the abundances for the yields. Wheat yields were then estimated with the four abundances, their relevant interactions, ten important agrometeorological vi parameters, including parameters proposed in this thesis for the first time, and four different vegetation indices using three different machine learning algorithms (Generalized Linear Model (GLM), Artificial Neural Network (ANN) and Random Forest (RF)). Harvester records from 142 wheat fields distributed in 31 provinces of Turkey were used as the ground truth for testing the algorithm. In the literature, the coefficient of determination (R2 ) is used as a proxy to show how good the relationship is between the estimated and real figures. According to these calculations, the yields were estimated with 64% accuracy when only the abundances were used in the GLM algorithm, 78% accuracy when ANN was used for yield estimation and 82% accuracy was reached when applying RF to all of the parameters. The similarity of the endmembers to photosynthetic pigment spectral signatures along with their predictive power suggested their relevance to the pigments. Although the R-CoNMF algorithm performs a linear unmixing of the intimate mixture of the photosynthetic pigments, the interactions of the abundances used in the endmember optimization and in classifications partially handle the nonlinearity using the bilinear model. These results can be considered as a great success when using multispectral satellite data only and are recognized as a clear indication that much better results would be achieved while using images from future hyperspectral space missions like HyspIRI.


Estimation of wheat yields by using remotely sensed and modeled agro-meteorological data-driven statistical and crop growth models
Bulut, Burak; Yılmaz, Mustafa Tuğrul; Department of Civil Engineering (2021-6)
Estimation of wheat yield is essential not only for agricultural sectors but also for making economic and strategic decisions at the national level. In this thesis, wheat yield estimation was carried out on the cities and districts where the highest wheat production is made with rainfed agriculture in Turkey and on TİGEM research farms. Two different modeling approaches were evaluated within the scope of the thesis; a statistical multiple linear regression (MLR) model based on analysis of possible agro-mete...
Sustainable design implications for alternative food networks: A case on Güneşköy's community supported agriculture (CSA) model
Kaplan, Ayşe; Doğan, Çağla; Department of Industrial Design (2021-6)
The global food system consists of complex processes (i.e., food production, distribution, consumption, and disposal) and contains several environmental, economic, and social sustainability challenges. As a result of the food system's problems, some producers and consumers have taken actions that have resulted in the emergence of alternative food networks. These are primarily bottom-up initiatives led by creative and innovative groups of people collaborating to develop alternative food-system solutions. Dif...
Early-age activation of cement pastes and mortars containing ground perlite as a pozzolan
Erdoğan, Sinan Turhan (Elsevier BV, 2013-04-01)
Perlite is a natural pozzolan abundant in several countries which are major producers of cement. This makes perlite attractive for producing sustainable concretes. Strength development and heat evolution of perlite-containing mixtures, and the influence of chemical and thermal activation on their early and later age properties were investigated using five activator chemicals and four curing temperature-duration combinations. Chemical activation could increase the 1-day, or 3-day compressive strengths of 25%...
Vulnerabilities, Threats and Gaps in Food Biosecurity
Fletcher, Jacqueline; Alpas, Hami; Henry, Christine M.; Haynes, Edward; Dehne, Heinz W.; Ma, Li Maria; Soyer, Yeşim; Yeni, Filiz; Colla, Paola; Robb, Paul (2017-01-01)
The food production system throughout the European Union, which includes farm production, harvesting, transport, processing, storage, marketing and consumption, is vast, complex and open. The high volume of trade in fresh vegetables and fruits contributes to the vulnerability to contamination, whether by accident or intent. Outbreak investigation is critical to understanding the sources of contamination and the steps required to minimize it. The fact that much of the trade in these commodities is internatio...
Development of human health risk-based Soil Quality Standards for Turkey: Conceptual framework
İpek, Meltem; Ünlü, Kahraman (2020-09-01)
Soil Quality Standards (SQSs) are considered as an important tool for management of contaminated sites. In order to manage adverse effects associated with soil contamination, risk-based SQSs are used worldwide. However, developing health risk-based SQSs is a challenging task. It involves comprehensive assessment of nationwide site characteristics (e.g. soil, hydrogeological, climatic properties), understanding of social behaviors that determine human exposure to soil pollutants (e.g. exposure scenarios and ...
Citation Formats
A. Özcan, “Early yield estimation by photosynthetic pigment abundances using landsat 8 image series,” M.S. - Master of Science, Middle East Technical University, 2020.