Cropping pattern classification using artificial neural networks and evapotranspiration estimation in the Eastern Mediterranean region of Turkey

Author:

ALSENJAR Omar1,ÇETİN Mahmut2,AKSU Hakan3ORCID,AKGÜL Mehmet Ali4,GOLPİNAR Muhammet Said5

Affiliation:

1. Cukurova

2. ÇUKUROVA ÜNİVERSİTESİ

3. SAMSUN UNIVERSITY

4. The Sixth Regional Directorate of State Hydraulic Works

5. CUKUROVA UNIVERSITY

Abstract

Determination of cropping pattern is a very important factor in quantifying irrigation water requirements at a catchment scale. In this regard, remote sensing is a robust tool for generating spatial-temporal variation of crops. This study focuses on crop classification by using remotely sensed data coupled with ground truth data. Therefore, this study aimed at both classifying each crop type and calculating crop evapotranspiration (ETc) based on reference evapotranspiration (ETo) by using the Penman-Monteith evapotranspiration model and crop coefficient (Kc). ETo was estimated by using data from two meteorological stations located in the study area. To this end, this study was conducted in Akarsu Irrigation District (≈95 km2), a sub-catchment in the Lower Seyhan Plain (LSP), in the 2021 hydrological year. Ground truth data were collected in the two growing seasons. The ENVI program was used to classify crop types from Sentinel 2A-2B satellite images with 10-m by 10-m spatial resolution. Image analysis results demonstrated that bare soil and citrus made up more than half of the area in the winter season, while corn and citrus were preponderant in summer. In addition, the total reference evapotranspiration and crop evapotranspiration were about 1308 mm and 890 mm, respectively in the 2021 water year. ETc values for second crop soybean, first crop corn, wheat, and citrus showed agreement with previous studies of direct methods of evapotranspiration in the Cukurova region. Furthermore, research findings led us to conclude that using remotely sensed satellite data in cropping pattern determination is promising in identifying the crops grown in large agricultural lands. Moreover, remote sensing images can be used to classify accurately crops in the winter and summer seasons, and this study has expanded the application value of remotely sensed data in large-scale irrigation schemes.

Publisher

Ankara University Faculty of Agriculture

Subject

Plant Science,Agronomy and Crop Science,Animal Science and Zoology

Reference29 articles.

1. Akpolat A (2011). Mikrometeorolojik ve lizimetre Yöntemleriyle Belirlenen Buğday Bitki Su Tüketimlerinin Karşılaştırılması. Yüksek Lisans Tezi. Çukurova Üniversitesi Fen Bilimleri Enstitüsü Tarımsal Yapılar ve Sulama Anabilim Dalı, Türkiye. (In Turkish)

2. Aksu H & Arikan A (2017). Satellite-based estimation of actual evapotranspiration in the Buyuk Menders Bain, Turkey. Hydrology Resarch 48(2):559-570 hhtps://doi.org/10.2166/nh.2016.226.

3. Aksu H, Cavus Y, Aksoy H, Akgul M.A, Turker S& Eris E (2022). Spatiotemporal analysis of drought by CHIRPS precipitation estimates. Theor Appl Climatol 148, 517–529 https://doi.org/10.1007/s00704-022-03960-6

4. Allen R. G, Pereira L. S, Raes D& Smith M (1998). Crop evapotranspiration - guidelines for computing crop water requirements. FAO irrigation and drainage paper 56, Fao, Rome, 300(9): D05109.

5. Belgiu M & Csillik O (2018.( Remote Sensing of Environment Sentinel-2 cropland mapping using pixel-based and object-based time-weighted dynamic time warping analysis. Remote Sensing of Environment, 204, pp: 509-523.

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3