光谱学与光谱分析
光譜學與光譜分析
광보학여광보분석
SPECTROSCOPY AND SPECTRAL ANALYSIS
2010年
5期
1295-1300
,共6页
叶旭君%Kenshi Sakai%何勇
葉旭君%Kenshi Sakai%何勇
협욱군%Kenshi Sakai%하용
柑橘%PLS%MLR%ANN%预测模型%变量技术%精细农业
柑橘%PLS%MLR%ANN%預測模型%變量技術%精細農業
감귤%PLS%MLR%ANN%예측모형%변량기술%정세농업
Citrus%PLS%MLR%ANN%Prediction model%Variable rate technology%Precision agriculture
果树的隔年结果现象严重影响果园的果实产量和经济效益.选择受隔年结果现象影响较为严重的柑橘作为研究对象,运用机载高光谱成像仪在较早生长季节(2003年4、5、6月)获取柑橘果树的高光谱图像,利用偏最小二乘回归(PLS)确定基于高光谱图像数据的模型预测变量,建立柑橘产量的多元线性回归(MLR)和人工神经网络(ANN)预测模型.研究结果表明,利用5月份获得的高光谱图像建立的模犁具有最优的产量预测效果,而且PLS-MLR模型比PLS-ANN模型具有更好的稳定性和一致性.该研究结果为今后研制和开发基于高光谱成像技术的柑橘产量预测方法提供了重要的理论和技术基础.
果樹的隔年結果現象嚴重影響果園的果實產量和經濟效益.選擇受隔年結果現象影響較為嚴重的柑橘作為研究對象,運用機載高光譜成像儀在較早生長季節(2003年4、5、6月)穫取柑橘果樹的高光譜圖像,利用偏最小二乘迴歸(PLS)確定基于高光譜圖像數據的模型預測變量,建立柑橘產量的多元線性迴歸(MLR)和人工神經網絡(ANN)預測模型.研究結果錶明,利用5月份穫得的高光譜圖像建立的模犛具有最優的產量預測效果,而且PLS-MLR模型比PLS-ANN模型具有更好的穩定性和一緻性.該研究結果為今後研製和開髮基于高光譜成像技術的柑橘產量預測方法提供瞭重要的理論和技術基礎.
과수적격년결과현상엄중영향과완적과실산량화경제효익.선택수격년결과현상영향교위엄중적감귤작위연구대상,운용궤재고광보성상의재교조생장계절(2003년4、5、6월)획취감귤과수적고광보도상,이용편최소이승회귀(PLS)학정기우고광보도상수거적모형예측변량,건립감귤산량적다원선성회귀(MLR)화인공신경망락(ANN)예측모형.연구결과표명,이용5월빈획득적고광보도상건립적모리구유최우적산량예측효과,이차PLS-MLR모형비PLS-ANN모형구유경호적은정성화일치성.해연구결과위금후연제화개발기우고광보성상기술적감귤산량예측방법제공료중요적이론화기술기출.
The phenomenon of alternate bearing of fruits seriously affects the fruit yields as well as the economic benefits of orchards.The present study investigated the possibility of airborne hyperspectral images to predict the fruit yield of individual citrus trees.The hyperspectral data were first extracted from the images and the predictors were determined using partial leastsquares regression (PLS).The optimal number of PLS factors were identified,and they were used as inputs of citrus yield prediction models developed by means of multiple linear regression (MLR) and artificial neural network (ANN) modelling techniques.The results showed that the models based on the hyperspectral images obtained in May achieved the best prediction,and the PLS-MLR model has a better stability and consistency than the PLS-ANN model.These results proviode an important theoretical and technical foundation for the future research and development of hyperspectral imaging-based citrus production techniques.