本文選題：土壤有機(jī)質(zhì)　切入點(diǎn)：極限學(xué)習(xí)機(jī)　出處：《土壤通報(bào)》2017年01期 　論文類型：期刊論文

【摘要】：應(yīng)用多源輔助變量預(yù)測土壤有機(jī)質(zhì)的空間分布,能有效提高預(yù)測精度。以西安市蔬菜產(chǎn)地為研究區(qū)域,共采集422個土壤樣品,運(yùn)用極限學(xué)習(xí)機(jī)(extreme learning machine,ELM)、逐步線性回歸(stepwise linear regression,SLR)、支持向量機(jī)(support vector machine,SVM)和隨機(jī)森林(random forest,RF)模型,結(jié)合坡度、坡向、種植年限、種植類型、灌溉方式、氮肥施用量、磷肥施用量、鉀肥施用量、土壤類型、堿解氮、有效磷、速效鉀、鹽分、硝酸鹽、pH值等15個多源輔助變量,對研究區(qū)蔬菜地土壤有機(jī)質(zhì)含量進(jìn)行空間預(yù)測,并通過100個實(shí)測點(diǎn)驗(yàn)證預(yù)測結(jié)果。結(jié)果表明:ELM對土壤有機(jī)質(zhì)預(yù)測結(jié)果的均方根誤差為0.631 g kg-1,均方根誤差和預(yù)測集平均值的比值為0.037,二者均低于其他3種模型,ELM的相關(guān)系數(shù)為0.716,顯著高于SLR、SVM和RF,ELM的空間預(yù)測結(jié)果更接近土壤有機(jī)質(zhì)含量的真實(shí)情況。同時(shí),根據(jù)ELM分析結(jié)果及算法本質(zhì)闡釋其在土壤屬性領(lǐng)域應(yīng)用的地理學(xué)意義,也為其他土壤屬性空間預(yù)測引入了一種新方法。
[Abstract]:Using multiple auxiliary variables to predict the spatial distribution of soil organic matter can effectively improve the prediction accuracy. 422 soil samples were collected in Xi'an vegetable production area. Using extreme learning machine learning machine, stepwise linear regression model, support vector machine support vector machine (SVM) and random forest random for stave (RFRF) model, combining slope, slope direction, planting years, planting type, irrigation method, nitrogen fertilizer application rate, phosphate fertilizer application rate, slope, slope direction, planting years, planting type, irrigation mode, nitrogen fertilizer application rate, phosphate fertilizer application rate, The soil organic matter content of vegetable land in the study area was predicted by applying potassium fertilizer, soil type, alkali-hydrolyzed nitrogen, available phosphorus, available potassium, salt, nitrate pH value, and so on. The results show that the root-mean-square error is 0.631 g 路kg ~ (-1) and the ratio of root mean square error to the average value of prediction set is 0.037, which is lower than that of the other three models. The results show that the root-mean-square error of soil organic matter is 0.631 g 路kg ~ (-1) and the ratio of mean square root error to mean value of prediction set is 0.037. The correlation coefficient is 0.716, which is significantly higher than the spatial prediction results of SLR- SVM and RFNELM, which is closer to the true situation of soil organic matter content. According to the results of ELM analysis and the essence of the algorithm, this paper explains the geographical significance of its application in the field of soil attributes, and introduces a new method for spatial prediction of other soil attributes.
【作者單位】： 西北大學(xué)城市與環(huán)境學(xué)院;西安市農(nóng)業(yè)技術(shù)推廣中心;西安市農(nóng)產(chǎn)品質(zhì)量安全檢驗(yàn)監(jiān)測中心;西北大學(xué)信息科學(xué)與技術(shù)學(xué)院;
【基金】：教育部人文社會科學(xué)研究規(guī)劃項(xiàng)目(10YJA910010) 陜西省農(nóng)業(yè)科技攻關(guān)項(xiàng)目(2011K02-11) 西安市科技計(jì)劃項(xiàng)目(NC1402,NC150201) 西北大學(xué)“211工程”研究生自主創(chuàng)新項(xiàng)目(YZZ15013)資助
【分類號】：S153.6

【相似文獻(xiàn)】

相關(guān)會議論文 前1條

1 陳美會;王先來;;精選—優(yōu)化輔助變量法閉環(huán)參數(shù)估計(jì)的收斂性[A];1994年中國控制會議論文集[C];1994年

相關(guān)碩士學(xué)位論文 前2條

1 蔡娟;輔助變量選擇在項(xiàng)目無回答插補(bǔ)方法中的應(yīng)用[D];天津財(cái)經(jīng)大學(xué);2013年

2 崔文麗;SRS和RSS下加入輔助變量信息后總體均值的比率估計(jì)[D];華中師范大學(xué);2013年

，

本文編號：1604306