【摘要】：土壤有機(jī)質(zhì)空間分布預(yù)測(cè)方法研究對(duì)指導(dǎo)省域尺度下土壤有機(jī)質(zhì)空間插值模型選取和精度優(yōu)化具有重要意義。以江西省為例,利用BP神經(jīng)網(wǎng)絡(luò)模型與普通克里金結(jié)合的方法(BPNN-OK)、RBF神經(jīng)網(wǎng)絡(luò)模型與普通克里金結(jié)合的方法(RBFNN-OK)以及普通克里金法(OK)3種方法,預(yù)測(cè)省域尺度下耕地表層(0~20 cm)土壤有機(jī)質(zhì)的空間分布。16 109個(gè)土壤樣點(diǎn)隨機(jī)分成12 887個(gè)建模樣點(diǎn),3 222個(gè)測(cè)試樣點(diǎn)。結(jié)果表明:在省域尺度下,BPNN-OK法、RBFNN-OK法較OK法在土壤有機(jī)質(zhì)空間預(yù)測(cè)精度上有較大提升,三者的預(yù)測(cè)精度為BPNN-OKRBFNN-OKOK。BPNN-OK法對(duì)土壤有機(jī)質(zhì)預(yù)測(cè)結(jié)果的均方根誤差、平均絕對(duì)誤差、平均相對(duì)誤差較OK法分別降低28.66%、30.71%、34.76%,RBFNN-OK法較OK法分別降低27.76%、29.74%、33.71%。在省域尺度下,神經(jīng)網(wǎng)絡(luò)模型與普通克里金結(jié)合的方法能很好地捕捉土壤有機(jī)質(zhì)的復(fù)雜空間變異關(guān)系。研究結(jié)果可指導(dǎo)江西省土壤有機(jī)質(zhì)空間插值模型選取。
[Abstract]:The prediction method of soil organic matter spatial distribution is of great significance to guide the spatial interpolation model selection and precision optimization of soil organic matter in provincial scale. Taking Jiangxi Province as an example, using the BP neural network model and the ordinary Kriging method (BPNN-OK), there are three methods, the RBFNN-OK method and the (OK) method, which are combined with the common Kriging neural network model and the common Kriging neural network model, respectively. The spatial distribution of soil organic matter on the surface of cultivated land (0 ~ 20 cm) was predicted. 16 109 soil samples were randomly divided into 12 887 pattern sites and 3 222 test sites. The results showed that the precision of spatial prediction of soil organic matter by BPNN-OK method was much higher than that by OK method at the provincial scale. The accuracy of the three methods was the root mean square error and the average absolute error of BPNN-OKRBFNN-OKOK.BPNN-OK method for soil organic matter prediction. The average relative error was decreased by 28.660.71% and 34.76% respectively compared with the OK method. The RBFNN-OK method was 27.76% lower than the OK method (29.74%) and 33.71% lower than that of the OK method. On the provincial scale, the neural network model combined with the ordinary Kriging method can capture the complex spatial variability of soil organic matter. The results can guide the selection of spatial interpolation model of soil organic matter in Jiangxi Province.
【作者單位】： 江西農(nóng)業(yè)大學(xué)國(guó)土資源與環(huán)境學(xué)院/江西省鄱陽(yáng)湖流域農(nóng)業(yè)資源與生態(tài)重點(diǎn)實(shí)驗(yàn)室;南方糧油作物協(xié)同創(chuàng)新中心;
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目(41361049) 江西省自然科學(xué)基金項(xiàng)目(20122BAB204012) 江西省贛鄱英才“555”領(lǐng)軍人才項(xiàng)目(201295)
【分類(lèi)號(hào)】：S153.621

【相似文獻(xiàn)】

相關(guān)期刊論文 前4條

1 魏周會(huì);龔少紅;馮小明;;作物產(chǎn)量預(yù)測(cè)的時(shí)間序列神經(jīng)網(wǎng)絡(luò)模型[J];節(jié)水灌溉;2006年06期

2 米湘成,馬克平,鄒應(yīng)斌;人工神經(jīng)網(wǎng)絡(luò)模型及其在農(nóng)業(yè)和生態(tài)學(xué)研究中的應(yīng)用[J];植物生態(tài)學(xué)報(bào);2005年05期

3 李容物,劉金福;七里街水文站實(shí)時(shí)洪水預(yù)報(bào)神經(jīng)網(wǎng)絡(luò)模型[J];福建林學(xué)院學(xué)報(bào);1999年04期

4 任承輝,楊學(xué)震,洪雙旌,陳明華;利用神經(jīng)網(wǎng)絡(luò)理論實(shí)現(xiàn)對(duì)水土流失快速遙感監(jiān)測(cè)[J];中國(guó)水土保持;2000年02期

，

本文編號(hào)：2252105