In recent years, frequent drought events in Konya, one of Türkiye's most important cereal production centres, have led to increased pressure on water and soil resources, resulting in yield losses, particularly in wheat production. Alternative yield prediction models, especially those that play a crucial role in agricultural import–export planning in the region, are important for economic contributions and the development of early warning systems. In this context, the aim of this study is to develop models that can be used in the yield prediction of wheat varieties widely grown in the Konya Altınova region. Agricultural drought indices obtained from Normalized Difference Vegetation Index (NDVI) and land surface temperature (LST) products of the Terra Moderate Resolution Imaging Spectroradiometer (MODIS) satellite were used to obtain model inputs. These indices are the Vegetation Condition Index (VCI), Temperature Condition Index (TCI), Vegetation Health Index (VHI) and Vegetation Supply Water Index (VSWI). In obtaining the input parameters for the models, the growth periods of the varieties in the region were also considered. Using various machine learning algorithms, 21 yield prediction models for Bayraktar‐2000, 12 for Kızıltan‐91 and 8 for Bezostaya‐1 were presented as alternatives, with model performances (coefficient of determination, R2) ranging between 0.74 and 0.97, 0.73 and 0.96, and 0.69 and 0.87, respectively.
{"title":"Yield prediction models for some wheat varieties with satellite‐based drought indices and machine learning algorithms","authors":"Muhammed Cem Akcapınar, Belgin Çakmak","doi":"10.1002/ird.2989","DOIUrl":"https://doi.org/10.1002/ird.2989","url":null,"abstract":"In recent years, frequent drought events in Konya, one of Türkiye's most important cereal production centres, have led to increased pressure on water and soil resources, resulting in yield losses, particularly in wheat production. Alternative yield prediction models, especially those that play a crucial role in agricultural import–export planning in the region, are important for economic contributions and the development of early warning systems. In this context, the aim of this study is to develop models that can be used in the yield prediction of wheat varieties widely grown in the Konya Altınova region. Agricultural drought indices obtained from Normalized Difference Vegetation Index (NDVI) and land surface temperature (LST) products of the Terra Moderate Resolution Imaging Spectroradiometer (MODIS) satellite were used to obtain model inputs. These indices are the Vegetation Condition Index (VCI), Temperature Condition Index (TCI), Vegetation Health Index (VHI) and Vegetation Supply Water Index (VSWI). In obtaining the input parameters for the models, the growth periods of the varieties in the region were also considered. Using various machine learning algorithms, 21 yield prediction models for Bayraktar‐2000, 12 for Kızıltan‐91 and 8 for Bezostaya‐1 were presented as alternatives, with model performances (coefficient of determination, R2) ranging between 0.74 and 0.97, 0.73 and 0.96, and 0.69 and 0.87, respectively.","PeriodicalId":505999,"journal":{"name":"Irrigation and Drainage","volume":"19 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141382074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Julianna Catonio da Silva, George do Nascimento Araújo Júnior, Adolpho Emanuel Quintela da Rocha, Thieres George Freire da Silva, Iêdo Peroba de Oliveira Teodoro, José Wanderson Silva dos Santos, Márcio Aurélio Lins dos Santos, Iêdo Teodoro, G. Lyra, Ceres Duarte Guedes Cabral de Almeida, Alexsandro Cláudio dos Santos Almeida
Sesame irrigation is essential in drought‐prone regions. However, information about the water needs of sesame is scarce. Therefore, the objective of this study was to determine crop evapotranspiration (ETc) and the sesame crop coefficient (Kc) during the rainy (S1) and dry (S2) seasons in the coastal tablelands of Alagoas, Brazil. The BRS Seda cultivar was grown in Rio Largo, Alagoas, Brazil, between 2021 and 2022. A system with 25 drainage lysimeters was installed to estimate the daily and cumulative ETc and the Kc for the entire crop cycle. The ETc was partitioned into transpiration (T) and evaporation (E), and the basal crop coefficients (Kcb) and soil evaporation coefficients (Ke) were subsequently estimated. The daily and cumulative ETc were 3.04 mm day−1 and 450.4 mm cycle−1, respectively, in S1 and 3.52 mm day−1 and 440.1 mm cycle−1, respectively, in S2. Regardless of the season, T was the main water flux (74%–80% of the ETc). The mean values of Kc were similar for S1 (0.79) and S2 (0.75), and Kcb and Ke followed the same trend as T and E, respectively. The accumulated ETc and Kc of sesame cultivated in the coastal tablelands of Alagoas, Northeast Brazil, are similar for the rainy and dry seasons.
芝麻灌溉对干旱地区至关重要。然而，有关芝麻需水量的信息却很少。因此，本研究旨在确定巴西阿拉戈斯州沿海台地雨季（S1）和旱季（S2）的作物蒸散量（ETc）和芝麻作物系数（Kc）。2021 年至 2022 年期间，巴西阿拉戈斯州里约拉尔戈种植了 BRS Seda 栽培品种。该系统安装了 25 个排水溶样器，用于估算整个作物周期的每日和累积蒸散发量以及 Kc。蒸散发分为蒸腾（T）和蒸发（E）两部分，随后估算出作物基础系数（Kcb）和土壤蒸发系数（Ke）。在 S1，日蒸发量（ETc）和累积蒸发量（ETc）分别为 3.04 毫米/天-1 和 450.4 毫米/周-1；在 S2，日蒸发量（ETc）和累积蒸发量（ETc）分别为 3.52 毫米/天-1 和 440.1 毫米/周-1。无论哪个季节，T 都是主要的水通量（占蒸散发的 74%-80% ）。Kc 的平均值在 S1（0.79）和 S2（0.75）中相似，Kcb 和 Ke 分别与 T 和 E 的趋势相同。巴西东北部阿拉戈斯州沿海台地种植的芝麻在雨季和旱季的累积蒸散发和 Kc 相似。
{"title":"Water requirement and single and dual crop coefficients of sesame cultivated in the coastal tablelands of Brazil","authors":"Julianna Catonio da Silva, George do Nascimento Araújo Júnior, Adolpho Emanuel Quintela da Rocha, Thieres George Freire da Silva, Iêdo Peroba de Oliveira Teodoro, José Wanderson Silva dos Santos, Márcio Aurélio Lins dos Santos, Iêdo Teodoro, G. Lyra, Ceres Duarte Guedes Cabral de Almeida, Alexsandro Cláudio dos Santos Almeida","doi":"10.1002/ird.2988","DOIUrl":"https://doi.org/10.1002/ird.2988","url":null,"abstract":"Sesame irrigation is essential in drought‐prone regions. However, information about the water needs of sesame is scarce. Therefore, the objective of this study was to determine crop evapotranspiration (ETc) and the sesame crop coefficient (Kc) during the rainy (S1) and dry (S2) seasons in the coastal tablelands of Alagoas, Brazil. The BRS Seda cultivar was grown in Rio Largo, Alagoas, Brazil, between 2021 and 2022. A system with 25 drainage lysimeters was installed to estimate the daily and cumulative ETc and the Kc for the entire crop cycle. The ETc was partitioned into transpiration (T) and evaporation (E), and the basal crop coefficients (Kcb) and soil evaporation coefficients (Ke) were subsequently estimated. The daily and cumulative ETc were 3.04 mm day−1 and 450.4 mm cycle−1, respectively, in S1 and 3.52 mm day−1 and 440.1 mm cycle−1, respectively, in S2. Regardless of the season, T was the main water flux (74%–80% of the ETc). The mean values of Kc were similar for S1 (0.79) and S2 (0.75), and Kcb and Ke followed the same trend as T and E, respectively. The accumulated ETc and Kc of sesame cultivated in the coastal tablelands of Alagoas, Northeast Brazil, are similar for the rainy and dry seasons.","PeriodicalId":505999,"journal":{"name":"Irrigation and Drainage","volume":"34 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141384831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Accurate estimation of the surface wetted radius (R) and vertical wetted depth (Z) of wetting patterns in drip irrigation systems is crucial for ensuring that the designs of such systems are effective. This study compared 14 empirical models for estimating drip irrigation wetting patterns by assessing their accuracy using published measurement data and HYDRUS‐2D/3D simulations. The technique for order of preference by similarity to the ideal solution (TOPSIS) was employed to comprehensively rank the models. The results indicate that the empirical model proposed by Fan et al. (2023) (FY) exhibited the highest accuracy when the estimations of R and measured and simulated values were compared, with mean absolute error (MAE), root mean square error (RMSE), Nash–Sutcliffe modelling efficiency (NSE), and percent bias (PB) values of 2.2 cm, 3.4 cm, 0.79, and −7.1% and 5.2 cm, 7.0 cm, 0.50, and −14.1%, respectively. The empirical model proposed by Amin and Ekhmaj (2006) (AE) demonstrated the highest accuracy when the estimations of Z were compared with measured and simulated values, with MAE, RMSE, NSE and PB values of 1.7 cm, 2.0 cm, 0.95 and 4.15% and 4.4 cm, 5.9 cm, 0.82 and 4.7%, respectively. The comprehensive rankings of available models in the present study indicate that the FY model is the most universally applicable, followed by the Li et al. (2022) (LY) model, with comprehensive indices of 0.960 and 0.936, respectively. This research can aid in the selection of universally applicable, reliable and straightforward empirical models for estimating wetting patterns in drip irrigation systems.
{"title":"Empirical models for calculating soil wetting patterns under surface drip irrigation systems: A comprehensive analysis","authors":"Ge Li, Weibo Nie, Yuchen Li","doi":"10.1002/ird.2982","DOIUrl":"https://doi.org/10.1002/ird.2982","url":null,"abstract":"Accurate estimation of the surface wetted radius (R) and vertical wetted depth (Z) of wetting patterns in drip irrigation systems is crucial for ensuring that the designs of such systems are effective. This study compared 14 empirical models for estimating drip irrigation wetting patterns by assessing their accuracy using published measurement data and HYDRUS‐2D/3D simulations. The technique for order of preference by similarity to the ideal solution (TOPSIS) was employed to comprehensively rank the models. The results indicate that the empirical model proposed by Fan et al. (2023) (FY) exhibited the highest accuracy when the estimations of R and measured and simulated values were compared, with mean absolute error (MAE), root mean square error (RMSE), Nash–Sutcliffe modelling efficiency (NSE), and percent bias (PB) values of 2.2 cm, 3.4 cm, 0.79, and −7.1% and 5.2 cm, 7.0 cm, 0.50, and −14.1%, respectively. The empirical model proposed by Amin and Ekhmaj (2006) (AE) demonstrated the highest accuracy when the estimations of Z were compared with measured and simulated values, with MAE, RMSE, NSE and PB values of 1.7 cm, 2.0 cm, 0.95 and 4.15% and 4.4 cm, 5.9 cm, 0.82 and 4.7%, respectively. The comprehensive rankings of available models in the present study indicate that the FY model is the most universally applicable, followed by the Li et al. (2022) (LY) model, with comprehensive indices of 0.960 and 0.936, respectively. This research can aid in the selection of universally applicable, reliable and straightforward empirical models for estimating wetting patterns in drip irrigation systems.","PeriodicalId":505999,"journal":{"name":"Irrigation and Drainage","volume":"7 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141273446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：