国产日韩欧美一区二区三区三州_亚洲少妇熟女av_久久久久亚洲av国产精品_波多野结衣网站一区二区_亚洲欧美色片在线91_国产亚洲精品精品国产优播av_日本一区二区三区波多野结衣 _久久国产av不卡

?

光譜變換方法對黑土養(yǎng)分含量高光譜遙感反演精度的影響

2018-10-18 12:23張東輝趙英俊趙寧博楊越超
農(nóng)業(yè)工程學報 2018年20期
關鍵詞:包絡線黑土反射率

張東輝,趙英俊,秦 凱,趙寧博,楊越超

?

光譜變換方法對黑土養(yǎng)分含量高光譜遙感反演精度的影響

張東輝,趙英俊,秦 凱,趙寧博,楊越超

(核工業(yè)北京地質(zhì)研究院 遙感信息與圖像分析技術國家級重點實驗室,北京 100029)

高光譜遙感反演黑土養(yǎng)分含量時,光譜變換方法對提取精度具有顯著影響,為明確二者響應關系,提高反演精度和穩(wěn)定度,該文以黑龍江建三江地區(qū)為研究區(qū),引入航空高光譜成像系統(tǒng)CASI-1500,獲取380~1 050 nm數(shù)據(jù)進行分析。均勻采樣60個樣品,化驗獲得其有機質(zhì)、全氮、全磷和全鉀含量數(shù)據(jù),利用神經(jīng)網(wǎng)絡方法對有機質(zhì)含量、支持向量機對氮、磷、鉀含量進行建模。對比研究了重采樣(RE)、對數(shù)倒數(shù)(LR)、一階微分(FD)、包絡線去除(CR)和多元散射校正(MSC)變換5種光譜變換后的提取精度。結果表明:MSC、MSC、LR和RE光譜變換方法分別應用到有機質(zhì)、氮、磷和鉀特征波段的組合運算中,得出黑土養(yǎng)分含量的空間分布精度相對最高,預測樣本的決定系數(shù)分別為0.748、0.673、0.631和0.420。

遙感;土壤;模型;光譜變換法;神經(jīng)網(wǎng)絡;支持向量機

0 引 言

隨著高光譜遙感技術在生態(tài)評價領域的研究深入,開展光譜遙感反演與地球化學驗證,建立黑土養(yǎng)分快速評價技術體系,能為黑土資源管理提供科學依據(jù)。根據(jù)土壤不同養(yǎng)分的躍遷能級差不同,研究物質(zhì)吸收光譜曲線,得出物質(zhì)的各組成成分[1]。現(xiàn)實研究中,由于土壤的理化性質(zhì)、上覆狀況和環(huán)境擾動千差萬別,導致光譜特征和成分含量的對應關系難以準確建立。需要在大量可靠光譜數(shù)據(jù)積累的基礎上,通過統(tǒng)計學習方法,逐步發(fā)現(xiàn)這些對應關系,并在與實測結果綜合分析的基礎上,解釋對應關系的作用原理。

機載高光譜遙感在獲取光譜數(shù)據(jù)同時,采集了高精度的空間數(shù)據(jù),使得研究土壤多種成分的空間分布關系成為可能,進而能夠計算出物質(zhì)間賦存和轉運關系。由于直接從土壤光譜中提取稀有元素的困難性,這種賦存關系的掌握,將為高光譜在這一領域研究的拓展提供技術手段。在獲取土壤光譜后,需要經(jīng)過光譜異常篩選、平滑去噪、重采樣、光譜變換和光譜定量化計算等處理方法,而其中的光譜變換方法,能夠起到增強有價值波段信息,提高建模精度的作用[2]。光譜變換的目的是通過將原始反射率進行轉換,形成一系列反射率自變量,這種自變量能夠放大或者縮小特征峰的反射率值,提升光譜識別的概率[3]。在與理化成分分析數(shù)據(jù)建立回歸模型時,經(jīng)過多種方法的綜合驗證,分析光譜數(shù)據(jù)和化驗數(shù)據(jù)的匹配關系[4]。

何挺等對土壤光譜進行了14種變換,研究了土壤光譜反射特性與有機質(zhì)之間的關系,證明反射率對數(shù)的一階微分對土壤有機質(zhì)含量最為敏感[5]。劉煥軍等[6]通過對典型黑土可見光/近紅外波段光譜反射特性研究,得出歸一化變換可以部分消除不同土樣測試過程中存在的噪聲。Andreas Steinberg等通過對不同有機質(zhì)含量土壤的光譜曲線吸收特征進行分析,得出包絡線去除和反射率的倒數(shù)的對數(shù)處理建立的偏最小二乘回歸模型預測效果最佳[7]。方少文等研究表明土壤全氮與一階微分轉換后反射率相關系數(shù)較高的峰值位置在820、1 400、1 430、1 630、1 800、1 930 nm等波段[8]。

黑土光譜在可見/近紅波段范圍內(nèi)反射率普遍較低,吸收特征不顯著,且易受水分和秸稈等因素的干擾,直接使用測量光譜所建立的反演模型的推廣性受到限制[9]。本文以黑龍江建三江地區(qū)黑土樣本為研究對象,對黑土光譜進行重采樣、對數(shù)倒數(shù)、一階微分、包絡線去除和多元散射校正等變換,建立了其有機質(zhì)、氮、磷、鉀等養(yǎng)分含量的定量提取模型,通過對比模型預測值與實測值的誤差,對5種光譜變換方法的適用性進行了研究,以期為光譜變換方法的選擇提供科學參考。

1 材料與方法

1.1 研究區(qū)概況

研究區(qū)位于黑龍江省建三江地區(qū),系黑龍江、松花江、烏蘇里江匯流的河間地帶。以盛產(chǎn)綠色優(yōu)質(zhì)水稻聞名,故有“中國綠色米都”之譽。地勢低平,地形標高50~60 m。由黃土狀粉質(zhì)黏土、淤泥質(zhì)粉質(zhì)粘土構成,主要分布于山前臺地頂部[10]。腐殖質(zhì)富集,加之母質(zhì)黏重,水不能迅速下滲,緩慢淋濾形成黑土層[11]。表層為黑色腐殖質(zhì)層,厚30~60 cm,最厚可達1m以上,多具圓柱狀或粒狀結構;其下為質(zhì)地黏重的淀積層,棕色鐵錳結核一般較多,再下為棕黃色粘性母質(zhì)層[12]。

1.2 數(shù)據(jù)來源

數(shù)據(jù)由CASI-1500航空高光譜成像光譜系統(tǒng)(加拿大ITRES)獲取。光譜范圍為380~1 050 nm,空間分辨率為1.5 m,連續(xù)光譜通道數(shù)55,光譜帶寬10 nm,總視場角40°,瞬時視場角0.028°,每行像元數(shù)1 470,絕對輻射精度<2%。飛行高度3 km(圖1)。地面測量鋪設黑白布,采用ASD Field Spec光譜儀獲取定標光譜,光譜范圍為350~2 500 nm,采集光譜分辨率為1 nm。

1.3 土壤樣采集與化學測定

研究區(qū)長9.27 km,寬5.36 km,面積約50 km2。采樣點60個,樣本1的坐標為132.747°E,47.232°N,樣本60的坐標為132.857°E,47.272°N,按0.75km間隔采集土樣,采樣時間為飛行作業(yè)同步采樣。測區(qū)表層為黑色腐殖質(zhì)層,厚30~60 cm,最厚可達1 m以上,多具圓柱狀或粒狀結構。當天同步采集表層0~20 cm的土樣,剔除大的植物殘茬、石礪等雜物,置于實驗室風干研磨,過0.15 mm篩選用于土壤養(yǎng)分含量測定。有機質(zhì)采用重鉻酸鉀容量-外加熱法測定,全氮、全磷和全鉀含量分別采用凱氏定氮法、NaOH堿熔鉬銻抗比色法和鉀火焰原子吸收分光光度法測定含量[5]。土壤養(yǎng)分含量測定結果中,樣本1~45用于訓練集,其余15個樣本用于預測(表1)。

圖1 研究區(qū)及樣點布置

表1 不同樣本點土壤養(yǎng)分含量信息表

1.4 光譜變換方法

選用R語言klap包實現(xiàn)支持向量機模型[13],AMORE包實現(xiàn)BP神經(jīng)網(wǎng)絡的建立,重采樣采用Mathlab實現(xiàn),航空高光譜波段運算由ENVI 5.3的bandmath實現(xiàn)。選用5種光譜變換算法試驗[14]。

1)重采樣(resampling,RE)

針對黑土光譜與養(yǎng)分含量提取的尺度不確定性問題[15],通過重采樣能夠確定最佳的提取波長間隔。計算公式為

式中D為采樣間隔;=D(D為偶數(shù));=D+1(D為奇數(shù))。

2)對數(shù)倒數(shù)(logarithmic reciprocal,LR)

光譜通過對數(shù)計算后,能夠成為相對值較近似的值,避免數(shù)據(jù)過大或過小[16]。倒數(shù)將這一新值轉換為同一量級的數(shù)據(jù),使之更具備可對比性[17]。計算公式為

式中Rnew_i為光譜變換后的新值;R為原始光譜反射率(下同)。

3)一階微分(first derivative,F(xiàn)D)

通過對反射光譜進行數(shù)據(jù)模擬,計算不同階的微分值迅速確定光譜變化點及最大最小反射率的波長位置。一階微分增強了光譜變化和壓縮的影響[18]。計算公式為

式中R+Di為與原始波段間隔一定范圍的光譜反射率;D為波長的間隔,視變換需要而定。

4)包絡線去除(continuum removal,CR)

包絡線去除可以有效突出光譜曲線的吸收和反射特征,并將反射率歸一化到0~1[19]。計算過程為:對光譜曲線上的所有“凸”出峰值點,比較大小,得到最大值點,作為包絡線的一個端點,計算該點與長波方向各個極大值點連線的斜率,以斜率最大點作為下一個包絡線端點進行循環(huán),直至最后一點;再以最大值點作為包絡線端點,向短波方向進行類似計算,以斜率最小點為下一端點進行循環(huán),直到曲線開始點;沿波長增加方向連接這些端點,即形成包絡線。

5)多元散射校正(multivariate scattering correction,MSC)

多元散射校正可以有效地消除散射影響,增強與成分含量相關的光譜吸收信息[20]。首先取所有光譜的平均光譜作為標準光譜,將每個樣品光譜與標準光譜進行一元線性回歸運算,計算各光譜相對于標準光譜的回歸常數(shù)和系數(shù),減去線性平移量,同時除以回歸系數(shù)修正光譜的基線相對傾斜,達到對每個光譜的基線平移和偏移都在標準光譜的參考下予以修正的目的,在不損失光譜吸收信息的前提下,提高了光譜的信噪比。計算公式為

2 結果與分析

2.1 養(yǎng)分含量與光譜關系分析

2.1.1 不同含量的黑土養(yǎng)分光譜特征

將60個黑土樣本按養(yǎng)分含量大小排序,分析在可見-近紅波段范圍內(nèi)光譜變換規(guī)律[21]。一是通過光譜特性與含量的機理分析,有機質(zhì)和氮元素的光譜特征較為明顯,而磷和鉀含量與光譜反射率整體的走勢關系不顯著;二是所選取的60個采樣點,有機質(zhì)和氮元素含量建模樣本區(qū)分度較好,標準偏差達到0.23和0.09,而全磷和全鉀的標準偏差僅為0.03和0.02,微小的含量差異導致較難得出回歸系數(shù)較好的模型。試驗結果也表明,標準偏差越好,所建模型的回歸系數(shù)就越高。鑒于論文重點研究光譜變換方法對四種養(yǎng)分提取的影響,而建立精度更高回歸系數(shù)數(shù)學模型不是論文的研究重點,在相同數(shù)學模型下,橫向對比四種光譜變換方法是有一定意義的[22]。

圖2為不同含量的黑土養(yǎng)分光譜特征圖。每個區(qū)間范圍取2條光譜曲線進行分析,得出隨著有機質(zhì)含量增高,黑土反射率逐漸降低(圖2a)。其中,8號樣品有機質(zhì)達到4.46 g/kg,反射率顯著低于其他樣品;而41號和53號樣品有機質(zhì)質(zhì)量分數(shù)在3.3 g/kg左右,其反射率明顯高于總體光譜均值。當有機質(zhì)含量較低時,由于土壤含水量和混合像元等干擾,這一規(guī)律會逐漸減弱,直至不顯著。氮變化規(guī)律是與有機質(zhì)光譜曲線類似,隨著氮含量增高,反射率逐漸降低(圖2b)。其中,9號和50號樣品氮質(zhì)量分數(shù)高于2.28 g/kg,反射率低于其他樣品。而隨著氮元素含量的進一步減少,這一規(guī)律不顯著。由于磷元素含量相對較小,在光譜曲線上的反射特征不明顯,在可見-近紅光譜范圍內(nèi)的變換沒有顯著的規(guī)律(圖2c)。同樣,鉀元素含量在可見-近紅光譜范圍內(nèi)的變換也沒有顯著的規(guī)律(圖2d)。

圖2 不同黑土養(yǎng)分含量的光譜特征

2.1.2 土壤主要養(yǎng)分特征波段提取

對60個采樣點不同養(yǎng)分含量進行逐波段求反射率對養(yǎng)分的相關系數(shù)[23-25](圖3)。

結果表明,與其他土壤養(yǎng)分相比,有機質(zhì)各個波段相關系數(shù)最高,均值達到0.39,氮和磷相關系數(shù)接近,分別為0.28和0.30,鉀相關系數(shù)最低,為0.05。選取相關系數(shù)較高的前5個波段,作為建模波段[26]。有機質(zhì)為933.6、914.5、905、866.8和943.1 nm,氮為933.6、866.8、876.3、847.7和914.5 nm,磷為950、933.6、866.8、857.3和914.5 nm,鉀為523.7、771.5、571.4、695.3和533.2 nm。

圖3 逐波段光譜反射率與黑土養(yǎng)分含量的相關關系

2.2 變換方法對養(yǎng)分含量預測的影響

2.2.1 黑土養(yǎng)分含量預測方法

對黑土光譜分別進行重采樣(RE)、對數(shù)倒數(shù)(LR)、一階微分(FD)、包絡線去除(CR)和多元散射校正(MSC)變換等共計5種光譜數(shù)據(jù)[27]。對比了神經(jīng)網(wǎng)絡、支持向量機和偏最小二乘法對4種養(yǎng)分的提取精度,有機質(zhì)和全鉀信息提取精度最高的算法是神經(jīng)網(wǎng)絡法,誤差分別為1.21%和0.81%,而支持向量機算法在提取全氮和全磷信息時,驗證樣本的實測均值和預測均值完全吻合,精度最高。因此,選用神經(jīng)網(wǎng)絡法,對研究區(qū)內(nèi)所有航空高光譜數(shù)據(jù)進行有機質(zhì)和全鉀信息提取。采用支持向量機方法,對研究區(qū)內(nèi)全氮和全磷信息進行建模和提取[28]。

具體參數(shù)設置為:支持向量機模型類別選eps-regression,核函數(shù)選linear線性,采用試錯法計算最佳gamma和懲罰因子,gamma設置為10-5~10-1,懲罰因子選10、50和100,根據(jù)20遍交叉檢驗方式評價每次組合的錯誤偏差[29]。所建神經(jīng)網(wǎng)絡模型為一個3層神經(jīng)網(wǎng)絡,即5-3-1,含1個隱層,完成預測模型的建立。神經(jīng)元學習率為4,采用最小均方根誤差法設置訓練誤差函數(shù),隱藏層神經(jīng)元激勵函數(shù)為傳遞函數(shù)tansig,輸出層神經(jīng)元激勵函數(shù)為線性函數(shù)purelin,訓練權值更新方法為含有動量的自適應梯度下降法ADAPTgdwm[30]。

2.2.2 重采樣評估光譜尺度效應

理論上光譜分辨率越高,土壤養(yǎng)分特征波段越顯著,模型反演的精度越高[31]。而實際提取中,將多個波段進行合成,能夠降低噪聲的干擾,提高模型的魯棒性[11]。因此,需要評估每種土壤養(yǎng)分提取的最佳光譜分辨率。將高光譜數(shù)據(jù)采樣為55、44、33、22和11個波段,提取特征波段的反射率,進行黑土養(yǎng)分提取。以15個預測樣本均方根誤差RMSE和模型決定系數(shù)2作為尺度效應評估指標,RMSE越小,說明模型的預測精度越高,2越大,模型的穩(wěn)定性越好[32]。

通過對比不同重采樣光譜的反演結果,在5種重采樣方法中,波段數(shù)55所建立的模型,均方根RMSE相對都最小或持平,而且模型決定系數(shù)2均是最高或持平,說明波段數(shù)的增多,能夠在一定程度上提升模型反演的精度。

2.2.3 建立響應關系模型

將原始光譜反射率集處理為重采樣RE、對數(shù)倒數(shù)LR、一階微分FD、包絡線去除CR和多元散射校正MSC反射率新值(圖4),利用神經(jīng)網(wǎng)絡方法對60個樣本的有機質(zhì)含量進行建模,利用支持向量機對60個樣本的氮、磷、鉀含量進行建模,得出其模型預測精度[33](表2)。

建模樣本中,有機質(zhì)、氮、磷和鉀光譜變換精度最高的方法分別是MSC(0.922)、MSC(0.872)、LR(0.621)和RE(0.423);預測樣本中,有機質(zhì)、氮、磷和鉀光譜變換精度排序與建模樣本一致,分別為MSC(0.748)、MSC(0.673)、LR(0.631)和RE(0.420)。建模樣本和預測樣本的均方根RMSE呈現(xiàn)出一致的排序規(guī)律,表明有機質(zhì)和全氮選擇MSC變換方法,而全磷和全鉀在LR和RE變換下,具有最高的模型決定系數(shù)和最低的均方根誤差。

圖4 黑土光譜的RE、LR、FD、CR和MSC處理結果(1號樣本點)

表2 不同光譜變換方法的土壤養(yǎng)分建模結果

2.3 提取結果

依次將決定系數(shù)較高的MSC、MSC、LR和RE光譜變換方法應用到有機質(zhì)、氮、磷和鉀特征波段的組合運算中,得出黑土養(yǎng)分含量的空間分布情況(圖5)。分析得出,研究區(qū)黑土養(yǎng)分含量空間分布呈現(xiàn)明顯的地塊規(guī)律,這與這一地區(qū)農(nóng)業(yè)開發(fā)較為成熟有關。不同的地塊由不同的農(nóng)戶種植,對地塊施肥、秸稈處理和灌溉休耕的處理各不相同,導致黑土養(yǎng)分的差異。總體上研究區(qū)有機質(zhì)和全氮分布規(guī)律近似,呈現(xiàn)出相似的分布規(guī)律。而磷元素和鉀元素由于含量較低,提取的誤差較大。

圖5 采用最佳光譜變換后的黑土養(yǎng)分含量(g·kg-1)提取空間分布圖

3 結 論

為提高光譜反演精度,將原始光譜反射率數(shù)據(jù)處理為重采樣RE、對數(shù)倒數(shù)LR、一階微分FD、包絡線去除CR和多元散射校正MSC等變換值。利用神經(jīng)網(wǎng)絡方法對60個樣本的有機質(zhì)含量進行建模,利用支持向量機對60個樣本的氮、磷、鉀含量進行建模。MSC、MSC、LR和RE光譜變換方法分別應用到有機質(zhì)、氮、磷和鉀特征波段的組合運算中,預測樣本的決定系數(shù)分別為0.748、0.673、0.631和0.420,得出黑土養(yǎng)分含量的空間分布精度相對最高。得出了每種黑土養(yǎng)分提取精度最佳的變換方法,以及五種光譜變換方法的提取精度差異,對于掌握光譜變換與黑土養(yǎng)分含量響應關系提供了定量依據(jù)。

[1] 史舟. 土壤地面高光譜遙感原理與方法[M]. 北京:科學出版社,2014.

[2] Daniel ?í?ala, Tereza Zádorová, Ji?í Kapi?ka. Assessment of soil degradation by erosion based on analysis of soil properties using aerial hyperspectral images and ancillary data[J]. Remote Sens, 2017, 9(1): 28-40.

[3] 周鼎浩,薛利紅,李穎,等. 基于可見–近紅外光譜的水稻土全磷反演研究[J]. 土壤,2014,46(1):47-52.

Zhou Dinghao, Xue Lihong, Li Ying, et al. Visible–near infrared reflectance spectroscopy for prediction of total phosphorus content in paddy soil[J]. Soil, 2014, 46(1): 47-52. (in Chinese with English abstract)

[4] 劉煥軍,潘越,竇欣,等. 黑土區(qū)田塊尺度土壤有機質(zhì)含量遙感反演模型[J]. 農(nóng)業(yè)工程學報,2018,34(1):127-133.

Liu Huanjun, Pan Yue, Dou Xin, et al. Soil organic matter content inversion model with remote sensing image in field scale of black soil area[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(1): 127-133. (in Chinese with English abstract)

[5] 何挺,王靜,林宗堅,等. 土壤有機質(zhì)光譜特征研究[J]. 武漢大學學報:信息科學版,2006,31(11):975-979.

He Ting, Wang Jing, Lin Zongjian, et al. Spectral features of soil organic matter[J]. Geomatics and Information Science of Wuhan University, 2006, 31(11): 975-979. (in Chinese with English abstract)

[6] 劉煥軍,張柏,趙軍,等. 黑土有機質(zhì)含量高光譜模型研究[J]. 土壤學報,2007,44(1):27-32.

Liu Huanjun, Zhang Bai, Zhao Jun, et al. Spectral models for prediction of organic matter in black soil[J]. Acta Pedologica Sinica, 2007, 44(1): 27-32. (in Chinese with English abstract)

[7] Andreas Steinberg, Sabine Chabrillat, Antoine Stevens, et al. Prediction of common surface soil properties based on vis–nir airborne and simulated enmap imaging spectroscopy data: prediction accuracy and influence of spatial resolution[J]. Remote Sens, 2016, 8(7): 613-627.

[8] 方少文,楊梅花,趙小敏,等. 紅壤區(qū)土壤有機質(zhì)光譜特征與定量估算:以江西省吉安縣為例[J]. 土壤學報,2014,51(5):1003-1010. Fang Shaowen, Yang Meihua, Zhao Xiaomin, et al. Spectral characteristics and quantitative estimation of som in red soil typical of Ji’an county, Jiangxi Province[J]. Acta Pedologica Sinica, 2014, 51(5): 1003-1010. (in Chinese with English abstract)

[9] 薛利紅,周鼎號,李穎,等. 不同利用方式下土壤有機質(zhì)和全磷的可見近紅外高光譜反演[J]. 土壤學報,2014,51(5):993-1001.

Xue Lihong, Zhou Dinghao, Li Ying, et al. Prediction of soil organic matter and total phosphorus with vis-nir hyperspectral inversion relative to land use[J]. Acta Pedologica Sinica, 2014, 51(5): 993-1001. (in Chinese with English abstract)

[10] 張俊華,馬天成,賈科利. 典型龜裂堿土土壤光譜特征影響因素研究[J]. 農(nóng)業(yè)工程學報,2014,30(23):158-165.

Zhang Junhua, Ma Tiancheng, Jia Keli. Factors affecting spectral characteristics of typical takyr solonetzs[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2014, 30(23): 158-165. (in Chinese with English abstract)

[11] Jin Xiuliang, Song Kaishan, Du Jia, et al. Comparison of different satellite bands and vegetation indices for estimation of soil organic matter based on simulated spectral configuration [J]. Agricultural and Forest Meteorology, 2017, 244: 57-71.

[12] 馬馳. 基于Landsat 8吉林中北部地區(qū)土壤有機質(zhì)定量反演研究[J]. 干旱區(qū)資源與環(huán)境,2017,31(2):167-172.

Ma Chi. Study on the quantitative retrieval of soil organic matter in the north and middle part of Jilin based on Landsat 8[J]. Journal of Arid Land Resources and Environment, 2017, 31(2): 167-172. (in Chinese with English abstract)

[13] 李萍,趙庚星,高明秀,等. 黃河三角洲土壤含水量狀況的高光譜估測與遙感反演[J]. 土壤學報,2015,52(6):1262-1271.

Li Ping, Zhao Gengxing, Gao Mingxiu, et al. Hyperspectral estimation and remote sensing retrieval of soil water regime in the Yellow River delta[J]. Acta Pedologica Sinica, 2015, 52(6): 1262-1271. (in Chinese with English abstract)

[14] 呂杰,郝寧燕,史曉亮. 基于流形學習的土壤高光譜數(shù)據(jù)特征提取研究[J]. 干旱區(qū)資源與環(huán)境,2015,29(7):176-180.

Lü Jie, Hao Ningyan, Shi Xiaoliang. Extraction of hyperspectral characteristics of soil based on manifold learning[J]. Journal of Arid Land Resources and Environment, 2015, 29(7): 176-180. (in Chinese with English abstract)

[15] Zhang P, Li Y. Study on the comparisons of the establishment of two mathematical modeling methods for soil organic matter content based on spectral reflectance[J]. Spectroscopy and Spectral Analysis, 2016, 36(3): 903-910.

[16] 王昶,黃馳超,徐光輝,等. 近紅外光譜結合偏最小二乘法快速評估土壤質(zhì)量[J]. 土壤學報,2013,50(5):36-45.

Wang Chuang, Huang Chichao, Xu Guanghui, et al. Rapid evaluation of soil quality through a near infrared–partial least squares (NIR-PLS) method[J]. Acta Pedologica Sinica, 2013, 50(5): 36-45. (in Chinese with English abstract)

[17] Zhao H, Feng X, Xiao P. Contour extraction of green cover along urban roads from remote sensing imagery based on frequency domain features[J]. Remote Sensing Information, 2014, 29(3): 50-56.

[18] Doustfatemeh I, Baleghi Y. Comprehensive urban area extraction from multispectral medium spatial resolution remote-sensing imagery based on a novel structural feature[J]. International Journal of Remote Sensing, 2016, 37(18): 4225-4242.

[19] Andreas Steinberg, Sabine Chabrillat, Antoine Stevens, et al. Prediction of common surface soil properties based on Vis-NIR airborne and simulated EnMAP imaging spectroscopy data: Prediction Accuracy and Influence of Spatial Resolution[J]. Remote Sens, 2016, 8(7): 613-627.

[20] 李碩,汪善勤,張美琴,等. 基于可見長丘紅外光譜比較主成分回歸、偏最小二乘回歸和反向傳播神經(jīng)網(wǎng)絡對土壤氮的預測研究[J]. 光學學報,2012,32(8):0830001-0830005.

Li Shuo, Wang Shanqin, Zhang Meiqin, et al. Comparison among principal component regression,partial least squares regression and back propagation neural network for prediction of soil nitrogen with visible–near infrared spectroscopy[J]. Acta Optica Sinica, 2012, 32(8): 0830001-0830005. (in Chinese with English abstract)

[21] 徐永明,藺啟忠,王璐,等. 基于高分辨率反射光譜的土壤營養(yǎng)元素估算模型[J]. 土壤學報,2006,43(5):709-716.

Xu Yongming, Lin Qizhong, Wang Lu, et al. Model for estimating soil nutrient elements based on high resolution reflectance spectra[J]. Acta Pedologica Sinica, 2006, 43(5): 709-716. (in Chinese with English abstract)

[22] Yu L, Liu X B, Liu G Z, et al. Experiment research and analysis of spectral prediction on soil leaking oil content (In Chinese)[J]. Spectroscopy and Spectral Analysis, 2016, 36(4): 1116-1120.

[23] 洪長橋,鄭光輝,陳昌春. 蘇北濱海土壤碳酸鈣含量反射光譜估算研究[J]. 土壤學報,2016,53(5):1120-1128.

Hong Changqiao, Zheng Guanghui, Chen Changchun. Estimation of CaCO3content in coastal soil of north Jiangsu with reflectance spectroscopy[J]. Acta Pedologica Sinica, 2016, 53(5): 1120-1128. (in Chinese with English abstract)

[24] 王凱龍,熊黑鋼,張芳. 基于高光譜數(shù)據(jù)預測土壤堿化程度最佳模型及其影響因素的研究[J]. 土壤,2014,46(3):544-549.

Wang Kailong, Xiong Heigang, Zhang Fang. Optimal model of soil pH and influencing factors by using hyperspectral data[J]. Soils, 2014, 46(3): 544-549. (in Chinese with English abstract)

[25] 高燈州,曾從盛,章文龍,等. 閩江口濕地土壤全氮含量的高光譜遙感估算[J]. 生態(tài)學雜志,2016,35(4):952-959.

Gao Dengzhou, Zeng Congsheng, Zhang Wenlong, et al. Estimating of soil total nitrogen concentration based on hyperspectral remote sensing data in Minjiang River estuarine wetland[J]. Chinese Journal of Ecology, 2016, 35(4): 952-959. (in Chinese with English abstract)

[26] 汪善勤,舒寧,蔡崇法,等. 基于PCA和SRRI的潮土土壤屬性與田間光譜關系研究[J]. 土壤,2008,40(6):960-970.

Wang Shanqin, Shu Ning, Cai Chongfa, et al. Relationship between in situ spectroscopy and properties of fluvo-aquic soil based on PCA and SRRI[J]. Soils, 2008, 40(6): 960-970. (in Chinese with English abstract)

[27] 金慧凝,張新樂,劉煥軍,等. 基于光譜吸收特征的土壤含水量預測模型研究[J]. 土壤學報,2016,53(3):627-634.

Jin Huining, Zhang Xinle, Liu Huanjun, et al. Soil moisture predicting model based on spectral absorption characteristics of the soil[J]. Acta Pedologica Sinica, 2016, 53(3): 627-634. (in Chinese with English abstract)

[28] 張東輝,趙英俊,秦凱. 一種新的光譜參量預測黑土養(yǎng)分含量模型[J]. 光譜學與光譜分析,2018,38(9):1-5. Zhang Donghui, Zhao Yingjun, Qin Kai. A new model for predicting black soil nutrient content by spectral parameters[J]. Spectroscopy and Spectral Analysis, 2018, 38(9): 1-5. (in Chinese with English abstract)

[29] 李晨,張國偉,周治國,等. 濱海鹽土土壤水分的高光譜參數(shù)及估測模型[J]. 應用生態(tài)學報,2016,27(2):525-531.

Li Chen,Zhang Guowei,Zhou Zhiguo,et al. Hyperspectral parameters and prediction model of soil moisture in coastal saline[J]. Chinese Journal of Applied Ecology 2016, 27(2): 525-531. (in Chinese with English abstract)

[29] 柴思躍,馬維玲,劉高煥,等. GA-PLS方法提取土壤水鹽光譜特征的精度分析[J]. 遙感技術與應用,2015,30(4):638-644.

Chai Siyue, Ma Weiling, Liu Gaohuan, et al. Accuracy analysis of GA-PLS based soil water salinity hyperspectral characteristics mining approach[J]. Remote Sensing Technology and Application, 2015, 30(4): 638-644. (in Chinese with English abstract)

[31] 程先鋒,宋婷婷,陳玉,等. 滇西蘭坪鉛鋅礦區(qū)土壤重金屬含量的高光譜反演分析[J]. 巖石礦物學雜志,2017,36(1):60-69.

Cheng Xianfeng, Song Tingting, Chen Yu, et al. Retrieval and analysis of heavy metal content in soil based on measured spectra in the Lanping Zn-Pb mining area, western Yunnan Province[J]. Acta Petrologica ET Mineralogica, 2017, 36(1): 60-69. (in Chinese with English abstract)

[32] 任紅艷. 寶山礦區(qū)農(nóng)田土壤水稻系統(tǒng)重金屬污染的遙感監(jiān)測[B]. 南京:南京農(nóng)業(yè)大學,2008.

Ren Hongyan. Use of hyperimultiple spectral data in monitoring heavy metal pollution in soil-paddy plant system nearby Baoshan mines[J]. Nanjing Agricultural University, 2008. (in Chinese with English abstract)

[33] 陳松超,馮來磊,李碩,等. 基于局部加權回歸的土壤全氮含量可見-近紅外光譜反演[J]. 土壤學報,2015,52(2):312-319.

Chen Songchao, Feng Lailei, Li Shuo, et al. Vis-nir spectral inversion for prediction of soil total nitrogen content in laboratory based on locally weighted regression[J]. Acta Pedologica Sinica, 2015, 52(2): 312-319. (in Chinese with English abstract)

Influence of spectral transformation methods on nutrient content inversion accuracy by hyperspectral remote sensing in black soil

Zhang Donghui, Zhao Yingjun, Qin Kai, Zhao Ningbo, Yang Yuechao

(100029,)

In order to improve the precision and stability of the soil nutrient content inversion model in black soil area, taking Jiansanjiang area in Heilongjiang province as the study area, and the airborne hyperspectral imaging system CASI-1500 (380-1 050 nm) as the analysis data, the influence of different spectral transformation methods on the accuracy was researched. 60 samples were evenly sampled, and the contents of organic matter, total nitrogen, total phosphorus and total potassium were obtained through laboratory tests. The content of organic matter was determined by potassium dichromate capacity external heating method. The content of total nitrogen, total phosphorus and total potassium was determined by Kjeldahl method, NaOH alkali antimony colorimetric method and potassium flame atomic absorption spectrophotometry. 60 black soil samples were sorted according to nutrient content, and the spectral transformation in the visible near red range was analyzed. The change rule of organic matter is that the reflectance decreases with the increase of content. The change rule of nitrogen is similar to the spectral curve of organic matter. With the increase of nitrogen content, the reflectance decreases. The transformation of phosphorus and potassium in the visible near red spectrum is not significant. The nutrient correlation coefficients of 60 samples at different sampling points were calculated by spectral reflectance. The results show that the correlation coefficient of each band is the highest, the mean value is 0.39, the correlation coefficients of nitrogen and phosphorus are close to 0.28 and 0.30, and the correlation coefficient of potassium is the lowest, which is 0.05. The first 5 bands with high correlation coefficient are selected as modeling bands, that of organic matter is 933.6, 914.5, 905, 866.8 and 943.1 nm, and that of nitrogen is 933.6, 866.8, 876.3, 847.7 and 914.5 nm. The content of organic matter and support vector machine were used to model nitrogen, phosphorus and potassium contents. The extraction accuracies of 5 spectral transformations which are resampling (RE), logarithmic reciprocal (LR), first order derivative (FD), continuum removal (CR) and multivariate scatter correction (MSC) transformation are compared. The most accurate methods for the spectral transformation of organic matter, nitrogen, phosphorus and potassium are MSC, MSC, LR and RE, respectively. Five spectral transformation methods are used to calculate the2of each model, and the order of modeling accuracy for soil organic matter prediction is MSC (0.922) > RE (0.529) > LR (0.432) > CR (0.414) > FD (0.018). The modeling accuracy of multiple scattering correction transformation is significantly higher than that of the other four methods. The order of prediction accuracy or total phosphorus is MSC (0.872) > CR (0.387) > RE (0.256) > LR (0.029) > FD (0.012), and the prediction accuracy of the multivariate scattering correction transformation is also the highest. The highest prediction accuracies of total phosphorus and total potassium are LR (0.621) and RE (0.423). In turn, the MSC, MSC, LR and RE spectral transformation methods with high coefficient of determination are applied to the combined operation of the characteristics of organic matter, nitrogen, phosphorus and potassium, and the spatial distribution of nutrient content in black soil is obtained. The results show that the spectral transformation methods of MSC, MSC, LR and RE are applied to calculate soil organic matter, nitrogen, phosphorus and potassium, respectively, the spatial distribution accuracy of nutrient content in black soil is the highest, and the determination coefficients of predicted samples are 0.748, 0.673, 0.631 and 0.420, respectively.

remote sensing; soils; models; spectral transformation methods; neural networks; support vector machines

10.11975/j.issn.1002-6819.2018.20.018

TP79

A

1002-6819(2018)-20-0141-07

2018-03-07

2018-09-03

國家自然科學基金項目(41602333)、“十三五”裝備預先研究專項技術項目(32101080302)、遙感信息與圖像分析技術國家級重點實驗室重點基金(9140C720105140C72001)和中國地質(zhì)調(diào)查局項目(12120113073000)聯(lián)合資助

張東輝,博士,高級工程師,主要從事高光譜遙感技術與應用研究。Email:donghui222@163.com

張東輝,趙英俊,秦 凱,趙寧博,楊越超. 光譜變換方法對黑土養(yǎng)分含量高光譜遙感反演精度的影響[J]. 農(nóng)業(yè)工程學報,2018,34(20):141-147. doi:10.11975/j.issn.1002-6819.2018.20.018 http://www.tcsae.org

Zhang Donghui, Zhao Yingjun, Qin Kai, Zhao Ningbo, Yang Yuechao. Influence of spectral transformation methods on nutrient content inversion accuracy by hyperspectral remote sensing in black soil[J]. Transactions of the Chinese Society of Agricultural Engineering (Transactions of the CSAE), 2018, 34(20): 141-147. (in Chinese with English abstract) doi:10.11975/j.issn.1002-6819.2018.20.018 http://www.tcsae.org

猜你喜歡
包絡線黑土反射率
自然資源部:加強黑土耕地保護
添加木本泥炭和膨潤土對侵蝕退化黑土理化性質(zhì)的影響*
利用鏡質(zhì)組反射率鑒定蘭炭與煤粉互混樣的方法解析
基于Sentinel-2遙感影像的黑土區(qū)土壤有效磷反演
基于ISO 14692 標準的玻璃鋼管道應力分析
商品條碼印制質(zhì)量檢測參數(shù)
——缺陷度的算法研究
車燈反射腔真空鍍鋁反射率研究
寒地黑土無公害水產(chǎn)品健康養(yǎng)殖發(fā)展思路
由橢圓張角為直角的弦所在直線形成的“包絡”
拋體的包絡線方程的推導
房山区| 姜堰市| 广元市| 得荣县| 萝北县| 黄龙县| 集安市| 安仁县| 南涧| 周宁县| 堆龙德庆县| 溧水县| 乐清市| 泉州市| 静安区| 大兴区| 泸定县| 崇义县| 霍州市| 特克斯县| 灵台县| 普安县| 万年县| 哈巴河县| 九龙坡区| 高青县| 墨江| 鹤山市| 连山| 嘉定区| 新兴县| 荃湾区| 松原市| 黄平县| 建平县| 胶州市| 荆州市| 开化县| 外汇| 克拉玛依市| 财经|