摘要
为探索基于气象因子的河蟹产量估算方法,现利用2010—2022年兴化市河蟹产量和同期气象数据,与3种机器学习算法相结合,在5个关键生长阶段(放养期、第1~3次脱壳期、第4次脱壳期、第5次脱壳期和成熟捕捞期),构建河蟹产量估算模型。结果表明,在河蟹不同生长阶段,不同气象因子估算河蟹产量的精度差异显著。总体来说,基于支持向量机回归(SVR)算法所构建的河蟹产量估算模型要优于随机森林回归(RFR)算法和偏最小二乘回归(PLSR)算法,预测精度R^(2)在0.95~0.98,RMSE在24.07~35.14 kg/hm^(2)之间变化。在单一生长阶段中,在放养期的估算精度最高,R^(2)为0.98,RMSE为24.07 kg/hm^(2),在全生育期中模型预测精度R^(2)为0.92,RMSE为44.31 kg/hm^(2)。研究结果揭示了气象因子在不同生长阶段下估算河蟹产量的能力。
This study aims to estimate crab yield by using meteorological factors.The crab yield and meteorological factors were acquired at five key growth stages(stocking period,1st-3rd shelling period,4th shelling period,5th shelling period and mature fishing period)from 2010-2022 in Xinghua of Jiangsu.Meanwhile,the meteorological factors were used as the inputs for the three machine learning algorithms for the crab yield estimation.The three machine learning algorithms included the Random Forest Regression(RFR),Support Vector Regression(SVR),and Partial Least Squares Regression(PLSR).Finally,the estimation models were developed using Leave-One-Out cross validation under different growth stages.The results showed that the precision of estimating crab yield by different meteorological factors was significantly different at different growth stages.For the three machine learning algorithms,the SVR was found to be superior to the RFR and the PLSR(coefficient of determination,R^(2)=0.95-0.98,RMSE=24.07-35.14 kg/hm^(2)).In the single growth stage,the highest estimation accuracy was observed at the stocking period(R^(2)=0.98,RMSE=24.07 kg/hm^(2)).In the whole growth period,the estimation accuracy was(R^(2)=0.92,RMSE=44.31 kg/hm^(2)).Therefore,the meteorological factors can be expected to estimate crab yield under the different growth stages.
作者
吴芳
章雯
翟晓瑶
龚佳
张自强
袁昌洪
WU Fang;ZHANG Wen;ZHAI Xiaoyao;GONG Jia;ZHANG Ziqiang;YUAN Changhong(Xinghua Meteorological Administration,Xinghua 225700,Jiangsu,China;Taizhou Meteorological Administration,Taizhou 225300,Jiangsu,China;Nanxun Meteorological Administration,Huzhou 313001,Zhejiang,China)
出处
《农学学报》
2024年第10期53-60,共8页
Journal of Agriculture
基金
江苏省气象局指导性项目“兴化市大闸蟹气候品质评价指标及模型研究”(ZD202425)
泰州市气象局科研项目“基于气象条件下兴化市河蟹产量估算模型研究”(202205)。
