基于野外实测Vis-NIR光谱的土壤肥力估算研究——以湟水流域为例

为探讨野外实测光谱数据对土壤肥力的估算能力,采集青海省湟水流域表层0～ 20 cm土壤样品220份,同步测量其采样位置的野外实测光谱数据,实验室对土壤养分、机械组成含量以及pH值进行分析.基于上述数据,对野外实测光谱反射率进行多元散射校正(Multiplicative scatter correction,MSC)、S...     

双江县冰岛五寨古茶园土壤养分状况及肥力质量评价

研究双江县冰岛五寨古茶园土壤养分状况及肥力质量水平,为该地古茶园土壤养分管理提供科学依据。测定了冰岛五寨古茶园105个土壤样本的pH、有机质（OM）、碱解氮（AN）、有效磷（AP）、速效钾（AK）、全氮（TN）、全磷（TP）以及全钾（TK）8项土壤养分指标,以变异系数法确定权重,利用模糊数学隶属度函数模型计算土壤肥力综合指数;结合相关性分析与主成分分析,对冰岛五寨古茶园的土壤养分及肥力质量进行综合性评价。结果表明：冰岛五寨古茶园土壤pH值在4.70～6.16之间,均值为5.45;OM含量在14.97～123.24 g/kg之间,OM含量丰富;AN含量为78.17～327.37 mg/kg,其中冰岛老寨和糯伍两地均有4.76%的土壤处于Ⅲ级标准,存在供氮不足;AP含量储备充足,含量在10.35～474.54 mg/kg之间,冰岛老寨处于高位水平;AK含量在56.67～590.00 mg/kg之间,坝歪含量总体偏低,部分土壤缺乏钾素;TN、TP、TK的含量范围分别0.33～5.34、4.68～22.38、14.94～45.41 g/kg,TP、TK含量远高于优质茶园标准;相关性与主成分分析...     

可见-近红外与中红外光谱预测土壤养分的比较研究

对土壤养分的快速和准确测定有助于适时指导施肥。为进一步研究可见-近红外（350～2500 nm）与中红外光谱（4000～650 cm-1）对土壤养分的预测能力,以贵州省500个土样为例,对光谱进行Savitzky-Golay（SG）平滑去噪处理,再用标准正态化（SNV）方法进行基线校正,然后分别应用偏最小二乘回归（PLSR）和支持向量机（SVM）两种方法进行建模,探讨了可见-近红外和中红外光谱对土壤全氮（TN）、全磷（TP）、全钾（TK）和碱解氮（AN）、有效磷（AP）、速效钾（AK）共六种土壤养分的预测效果。结果表明：（1）无论基于可见-近红外光谱还是中红外光谱,PLSR模型的预测精度整体均优于SVM模型。（2）中红外光谱对TN、TK和AN的预测精度均显著高于可见-近红外光谱,可见-近红外和中红外光谱均可以可靠地预测TN和TK（性能与四分位间隔距离的比率（RPIQ）大于2.10）,中红外光谱可相对较可靠地预测AN（RPIQ=1.87）;但两类光谱对TP、AP和AK的预测效果均较差（RPIQ<1.34）。（3）当变量投影重要性得分（VIP）大于1.5时,PLSR模型在中红外光谱区域预测TN和TK的重要波段多于可见-近红外光谱区域,TN的重要波段主要集中于可见-近红外光谱区域的1910和2207 nm附近,中红外光谱区域的1 120、1 000、960、910、770和668 cm-1附近;TK的重要波段主要集中于可见-近红外光谱区域的540、2176、2225和2268 nm附近,中红外光谱区域的1 040、960、910、776、720和668 cm-1附近。因此,中红外光谱技术结合PLSR模型对土壤养分预测效果较好,可快速准确预测土壤TN和TK,可为指导适时施肥提供技术支撑。     

横断山区森林土壤饱和导水率传递函数的评价与构建研究

利用国际上具有代表性的9种土壤饱和导水率(Ks)传递函数模型估算了横断山地区贡嘎山不同类型森林土壤的K_s，并与实测数据进行了比较，结果表明，现有模型在横断山地区的拟合结果与实测数据的偏差极大，其在研究区的适用性差。结合研究区土壤含石率偏高的特点，增加土壤石砾含量(粒径>2 mm)作为输入变量，同时选取土壤容重、有机质含量和颗粒分布3种土壤基本特性参数作为输入变量，构建了本区域K_s传递函数模型：K_s=9.48+12.32×BD+0.29×SOM–1.94×GF+2.89×silt–5.34×sand，结果显示，模型预测值与实测值相关系数为0.67，该模型可以作为横断山地区自然林地K_s传递函数使用，从而为山地森林水文过程和自然灾害预警研究提供实用的参数估算工具。     

滨湖城市典型公园化河口岸带土壤理化性状研究

为摸清五里湖公园化河口岸带土壤理化性质,探明土壤质量状况,本研究于2017年10月对五里湖3个典型公园化河口区域(陆典桥浜L、梁塘河C、圩田里河W)的24个点位进行岸带土壤采集,分析土壤颗粒组成、容重(BD)和孔隙度(Pt)等物理性状和pH、有机质(OM)、全氮(TN)、碱解氮(AN)、全磷(TP)和有效磷(AP)等化学性状,并利用与植物生长相关的土壤指标(石砾、砂粒、黏粒、BD、pH、OM、TN、AN、TP、AP)进行土壤质量指数(SQI)评价。结果表明:①3个河口岸带土壤均存在结构退化的情况,土壤主要以石块和石砾为主(700g/kg),砂粒、粉粒和黏粒含量较低,土壤容重偏大(1.35 g/cm3),孔隙度偏低(50%);②3个河口岸带土壤pH均呈碱性(平均8.30),且陆典桥浜河口圩田里河河口梁塘河河口,AP含量趋势相反;除梁塘河河口TP含量差异不大外,陆典桥浜和梁塘河河口的OM、TN、AN、AP、TP均呈现近岸大于远岸的趋势。③3个河口岸带土壤质量状况均较差(SQI0.5),AN、BD、OM、AP和pH是影响研究区域岸带土壤质量的5个主因子。     

灌溉水中悬浮固体对土壤水分入渗性能的影响

为监测黑龙江省黑土典型区土壤的养分元素含量,综合利用统计理论与光谱分析方法,研究建三江农场黑土土壤的3类养分含量与土壤光谱之间的关系,建立土壤全氮、有效磷、速效钾含量高光谱反演模型,实现土壤养分元素含量定量预测。对黑土土壤航空高光谱数据进行处理,应用偏最小二乘回归（PLSR）和BP神经网络方法分别建立土壤养分元素含量的高光谱定量反演模型,结果表明：全氮PLSR和BP神经网络预测模型的RPIQ值（样本观测值第三和第一四分位数之差与均方根误差的比值）分别为2.42和2.80;有效磷PLSR和BP神经网络模预测型的RPIQ值分别为0.83和1.67;速效钾PLSR和BP神经网络模型的RPIQ值分别为2.00和2.33。试验证明土壤全氮和速效钾的光谱定量预测模型具备较好的精度和预测能力。但有效磷的预测效果不是特别理想,仅可达到近似定量预测的要求;BP神经网络建模相比偏最小二乘建模有更好的精度和预测能力,预测精度分别提高6.5%、10.1%和6.6%。     

黑土养分含量的航空高光谱遥感预测

为监测黑龙江省黑土典型区土壤的养分元素含量,综合利用统计理论与光谱分析方法,研究建三江农场黑土土壤的3类养分含量与土壤光谱之间的关系,建立土壤全氮、有效磷、速效钾含量高光谱反演模型,实现土壤养分元素含量定量预测。对黑土土壤航空高光谱数据进行处理,应用偏最小二乘回归（PLSR）和BP神经网络方法分别建立土壤养分元素含量的高光谱定量反演模型,结果表明：全氮PLSR和BP神经网络预测模型的RPIQ值（样本观测值第三和第一四分位数之差与均方根误差的比值）分别为2.42和2.80;有效磷PLSR和BP神经网络模预测型的RPIQ值分别为0.83和1.67;速效钾PLSR和BP神经网络模型的RPIQ值分别为2.00和2.33。试验证明土壤全氮和速效钾的光谱定量预测模型具备较好的精度和预测能力。但有效磷的预测效果不是特别理想,仅可达到近似定量预测的要求;全氮、有效磷和速效钾的预测精度,BP神经网络建模相比偏最小二乘建模有更好的精度和预测能力,预测精度分别提高6.5%、10.1%和6.6%。     

基于实测高光谱和Landsat 8 OLI影像的土壤盐化和碱化程度反演研究

针对宁夏银北地区土壤盐碱化定量监测的需要,利用实测土壤高光谱和Landsat 8 OLI多光谱影像数据采用多项式、多元线性回归等方法进行土壤含盐量和pH值反演研究,并对影像光谱反演模型进行校正,以提高遥感定量反演精度。结果表明:(1)基于实测光谱的土壤含盐量反演精度均高于基于OLI影像反演精度;基于实测光谱敏感波段反射率反演精度高于实测盐分指数反演精度,其中实测光谱经平滑后敏感波段建立的模型效果最佳(R~2=0.695)。(2)基于实测光谱平滑后敏感波段建立的pH值反演模型精度最高且最稳定(R~2=0.545),基于OLI影像光谱反演精度低于实测光谱,但也通过了显著性检验和精度验证。(3)经实测光谱模型校正后的Landsat 8 OLI影像光谱的土壤含盐量反演模型R~2从0.347提高到0.623。研究结果可以为准确、快速地定量监测当地土壤盐分含量、pH值的变化提供科学依据和技术手段。     

不同生育期水稻叶面积指数的高光谱遥感估算模型

2011年和2012年通过大田试验,利用便携式野外光谱仪实测水稻冠层不同生育时期的高光谱数据,同时使用SUNSCAN冠层分析系统采集水稻冠层叶面积指数（LAI）;采用光谱微分技术和统计分析技术,分别分析高光谱反射率及其植被指数与LAI之间的关系,建立LAI估算模型并进行模拟结果对比。结果表明：水稻抽穗-成熟期,利用光谱值的对数形式对LAI值的模拟效果较好,分蘖-抽穗期利用光谱反射率模拟LAI变化过程的效果不理想。 在利用各种植被指数估算LAI方法中,水稻分蘖-抽穗期以修改型土壤调整植被指数MSAVI[758,805]对LAI的估算效果最好,模拟值与实测值的相关系数通过了0.01水平的显著性检验（R=0.7754）,估算精度较高。在抽穗-成熟期,也以修改型土壤调整植被指数MSAVI[758,817]对LAI的模拟效果最好,模拟值与实测值的相关系数通过了0.01水平的显著性检验（R=0.6488）,估算精度较高。说明修改型土壤调整植被指数（MSAVI）能更好地模拟水稻不同生育期的叶面积指数,按照分蘖-抽穗期、抽穗-成熟期两个生育阶段分别建立水稻冠层LAI的高光谱估算模型能够提高LAI估算的准确度,研究结果也证实了分生育阶段建模的必要性。     

基于机器学习算法的湖滨绿洲土壤电导率高光谱估算模型

  目的  为湖滨绿洲土壤高光谱估算土壤电导率值提供方法支持,实现区域土壤盐分快速估测。  方法  利用实测的土壤电导率值与土壤高光谱数据联合分析,采用竞争自适应重加权采样（CARS）、连续投影算法（SPA）、遗传算法（GA）筛选土壤电导率的特征波段,并基于全波段及特征波段构建BP神经网络（BPNN）、支持向量机（SVM）、极限学习机（ELM）三种机器学习算法模型,引入偏最小二乘模型（PLSR）进行对照,比较其模型精度。  结果  研究区土壤电导率值变化范围0.02～17.22 mS cm?1,平均值为2.61 mS cm?1,变异系数为134.87%,呈现强变异性;CARS、SPA、GA算法筛选的特征波段将建模输入量分别压缩至全波段数量的0.87%、1.68%、0.70%,减少建模输入量,提升建模速率,变量方法的选择CARS > SPA > GA;三种机器学习算法模型均优于PLSR模型,决定系数（R2）平均增加20.57%,相对分析误差（RPD）平均增加17.84%,土壤电导率高光谱估算模型以CARS-SVM最优,训练集与验证集R2分别为0.76和0.75,RMSE分别为1.79 和1.68 mS cm?1,RPD分别为2.04和2.00。土层深度20 ~ 30 cm的土壤电导率高光谱估算模型精度最高,训练集与验证集R2分别为0.83和0.84,RMSE分别1.37和1.77 mS cm?1,RPD分别为2.41和2.50。  结论  基于CARS-SVM的土壤电导率高光谱估算模型精度高,估算能力最优,可以为湖滨绿洲土壤电导率估算提供科学参考。     

基于相似光谱匹配预测土壤有机质和阳离子交换量

土壤可见光-近红外波段光谱(350~2 500 nm)包含了大量的土壤属性信息,相同类型的土壤具有相似的光谱曲线特征,但相似光谱曲线是否具有相似的属性含量?探讨此问题可为土壤光谱库的应用提供依据,从而最终服务于快速获取土壤信息技术体系的构建。该研究以安徽宣城为研究区,根据母质、地形特征和土地利用等信息,采集91个典型土壤剖面,共含400个土壤发生层样品,测定了有机质(soil organic matter,SOM)和阳离子交换量(cation exchange capacity,CEC)含量,同时采用VARIAN公司的Cary 5000分光光度计测定了土壤光谱,并将光谱数据变换为反射率(R)、反射率一阶导数(FDR)和吸收度(Log(1/R))3种形式。该文采用光谱角(spectral angle mapper,SAM)、偏最小二乘回归(partial least square regression,PLSR)和SAM-PLSR(spectral angle mapper-partial least square regression,SAM-PLSR)3种方法预测土壤SOM和CEC。SAM方法是通过对测试集104个光谱曲线与参考集的296个光谱曲线进行相似性计算,并以此实现土壤SOM和CEC含量的预测。SAM-PLSR方法以SAM算法下的匹配结果作为建模样本建立PLSR模型和进行预测分析。结果表明,具有相似光谱曲线的土壤具有相似的SOM和CEC含量,SAM算法下相似光谱匹配可直接预测SOM(R2=0.78,RPD=2.17)和CEC(R2=0.82,RPD=2.41)。PLSR方法可很好地预测SOM(R2=0.87,RPD=2.77)和CEC(R2=0.87,RPD=2.59);相较之下,SAM-PLSR方法不仅可以更加准确预测SOM(R2=0.89,RPD=3.00)和CEC(R2=0.91,RPD=3.06),而且大大减少了建模样本的数量。该研究使可见光-近红外光谱可更加高效地用于土壤属性分析,并为土壤光谱数据库的建设及应用提供技术参考。     

Transferability and scalability of soil total carbon prediction models in Florida, USA

The applicability, transferability, and scalability of visible/near-infrared (VNIR)-derived soil total carbon (TC) models are still poorly understood. The objectives of this study were to: i) compare models of three multivariate statistical methods, partial least squares regression (PLSR), support vector machine (SVM), and random forest methods, to predict soil logarithm-transformed TC (logTC) using five fields (local scale) and a pooled (regional-scale) VNIR spectral dataset (a total of 560 TC spectral datasets), ii) assess the model transferability among fields, and iii) evaluate their up- and downscaling behaviors in Florida, USA. The transferability and up- and downscaling of the models were limited by the following factors: i) the spectral data domain, ii) soil attribute domain, iii) methods that describe the internal model structure of VNIR-TC relationships, and iv) environmental domain space of attributes that control soil carbon dynamics. All soil logTC models showed excellent performance based on all three methods with R² > 0.86, bias < 0.01%, root mean squared error (RMSE) = 0.09%, residual predication deviation (RPD) > 2.70%, and ratio of prediction error to interquartile range (RPIQ) > 4.54. The PLSR method performed substantially better than the SVM method to scale and transfer the TC models. This could be attributed to the tendency of SVM to overfit models, while the asset of the PLSR method was its robustness when the models were validated with independent datasets, transferred, and/or scaled. The upscaled soil TC models performed somewhat better in terms of model fit (R²), RPD, and RPIQ, whereas the downscaled models showed less bias and smaller RMSE based on PLSR. We found no universal trend indicating which of the four limiting factors mentioned above had the most impact that constrained the transferability and scalability of the models. Given that several factors can impinge on the empirically derived soil spectral prediction models, as demonstrated by this study, more focus on their applicability and scalability is needed.     

湘中南土地整理后烟田土壤肥力指标评价及空间变异特征

掌握土地整理区土壤养分特征已成为烟田快速培肥和提升土壤质量的首要问题。采用GIS与地统计学相结合的方法,评价了土地整理后烟田土壤养分等肥力指标的适宜性等级状况及其空间变异特征。结果表明:研究区土壤偏酸,有机质、碱解氮含量普遍缺乏,存在较大面积的缺钾现象;各肥力指标均属于中等变异,变异系数大小顺序依次为有效磷 > 速效钾 > 碱解氮 > 有机质 > 全氮 > 全磷 > 全钾 > pH值。有机质和速效钾的变异函数比较符合指数模型,全钾、碱解氮用高斯模型拟合效果好,而pH值、全磷、全氮和有效磷则以球状模型拟合效果最佳。肥力指标的块金系数[C₀/（C₀+C）]中,土壤有机质、全钾、碱解氮分别为0.903,0.998,0.823,空间相关性较弱;而pH值、全氮、全磷和有效磷的块金系数[C₀/（C₀+C）]变化范围为0.501~0.724,具有中等空间相关性;各肥力指标空间变程为99~1 003 m,最大和最小值分别为全钾和碱解氮;各肥力指标表现出不同的空间分布特征,其中,pH值呈斑块状,碱解氮及全钾呈条带状,全磷整体上呈从北至南含量增加的梯度分布格局。     

同时估测土壤全氮、有机质和速效氮含量的光谱指数研究

通过系统分析我国中、东部地区5种不同类型土壤风干样本的有机质、全氮及速效氮含量与近红外(1 000～2 500 nm)光谱反射率之间的关系,进而构建了适合同时估测这3种养分含量的光谱参数及定量估算模型。结果表明,同时与3种养分指标相关较高的波段范围为1 879～1 890与2 050～2 100 nm,其中1 881和2 070 nm两个波段的反射率经多元散射校正及Savitzky-Golay平滑处理并构建而成的差值指数DI(CR1 881,CR2 070)与土壤有机质、全氮及速效氮含量具有良好的线性相关性。独立的观测资料检验显示,基于DI(CR1 881,CR2 070)的估测模型对全氮、有机质和速效氮的预测决定系数R2分别为0.83、0.79和0.72,均方根误差(RMSE)分别为0.20 g kg-1、4.71 g kg-1和23.96 mg kg-1,相对分析误差(RPD)分别为2.56、2.30和2.93。表明DI(CR1 881,CR2 070)是一种可同时估测土壤中3种养分含量的良好光谱指数。     

结合高光谱信息的土壤有机碳密度地统计模型

传统线性回归模型在借助光谱信息进行土壤属性预测时,通常忽略了土壤自身所具有的空间异质性和依赖性,并且未考虑模型残差的空间结构。针对以上不足,该文以江汉平原232个土壤样本为研究对象,以土壤反射光谱为辅助变量,采用偏最小二乘回归、普通克里格、协同克里格以及回归克里格分别构建土壤有机碳密度预测模型,选取决定系数(R~2)、均方根误差、标准差与预测均方根误差比(ratio of performance to deviation,RPD)对模型预测精度进行对比评价。结果显示,结合高光谱信息,且同时考虑残差空间结构的回归克里格模型表现优于其他模型,预测决定系数R~2为0.617,RPD为1.614。鉴于土壤光谱信息同时还具有测定简单、省时、无损等优点,因此土壤光谱是土壤有机碳密度空间插值的理想辅助因子。     

Key soil nutrient requirements for different yield levels in North China

ABSTRACT

Soil chemical properties are closely related to crop production levels. Understanding the relationships between soil nutrients and different yield levels is important for improving the efficiency of fertilization management programs. The objectives of this study were to understand the key soil nutrient requirements for different crop yield levels using 10 experimental wheat-maize rotation sites and to optimize fertilization applications in North China. The results found significant differences between the soil chemical properties among the study sites, with average contents in the range of 10.07–14.72 g/kg for soil organic carbon (SOC), 0.38–1.29 g/kg for total nitrogen (TN), 56.43–89.77 mg/kg for available nitrogen (AN), 17.36–48.54 mg/kg for available phosphorus (AP), 79.4–184.5 mg/kg for available potassium (AK), 0.78–5.97 mg/kg for soil Cu, and 0.75–2.20 mg/kg for soil Zn. The soil pH values were 6.46–8.19. Significant correlations (p < 0.05) were found between high-level yields and higher contents of SOC, TN, AN, and AP when a suitable soil pH were present. The higher levels of soil SOC and TN were important for maintaining high-level yields in these regions. Soil AN and pH are two key limitations that could significantly (p < 0.05) improve medium-level yields. Although some soil indicators, including SOC, TN, AN, AP, soil pH, soil Zn, and Cu could significantly influence low-level yields, soil amendments with C, N, and available P and having a suitable soil pH were especially important for improving low-level yields. These results could be used to improve conventional methods of fertilization management and increase the efficiency of fertilizer use in North China.     

Using pXRF and vis-NIR spectra for predicting properties of soils developed in loess

Visible near-infrared (vis-NIR) and portable X-ray fluorescence (pXRF) spectrometers have been increasingly utilized for predicting soil properties worldwide. However, only a few studies have focused on splitting the predictive models by horizons to evaluate prediction performance and systematically compare prediction performance for A, B, and combined A+B horizons. Therefore, we investigated the performance of pXRF and vis-NIR spectra, as individual or combined, for predicting the clay, silt, sand, total carbon (TC), and pH of soils developed in loess, and compared their prediction performance for A, B, and A+B horizons. Soil samples (176 in A horizon and 172 in B horizon) were taken from Mollisols and Alfisols in 136 pedons in Wisconsin, USA and analyzed for clay, silt, sand, pH, and TC. The pXRF and vis-NIR spectrometers were used to measure the pXRF and vis-NIR soil spectra. Data were separated into calibration (n=244, 70%) and validation (n=104, 30%) datasets. The Savitzky-Golay filter was applied to preprocess the pXRF and vis-NIR spectra, and the first 10 principal components (PCs) were selected through principal component analysis (PCA). Five types of predictor, i.e., PCs from vis-NIR spectra, pXRF of beams at 0-40 and 0-10 keV (XRF40 and XRF10, respectively) spectra, combined XRF40 and XRF10 (XRF40+XRF10) spectra, and combined XRF40, XRF10, and vis-NIR (XRF40+XRF10+vis-NIR) spectra, were compared for predicting soil properties using a machine learning algorithm (Cubist model). A multiple linear regression (MLR) model was applied to predict clay, silt, sand, pH, and TC using pXRF elements. The results suggested that pXRF spectra had better prediction performance for clay, silt, and sand, whereas vis-NIR spectra produced better TC and pH predictions. The best prediction performance for sand (R²=0.97), silt (R²=0.95), and clay (R²=0.84) was achieved using vis-NIR+XRF40+XRF10 spectra in B horizon, whereas the best prediction performance for TC (R²=0.93) and pH (R²=0.79) was achieved using vis-NIR+XRF40+XRF10 spectra in A+B horizon. For all soil properties, the best MLR model had a lower prediction accuracy than the Cubist model. It was concluded that pXRF and vis-NIR spectra can be successfully applied for predicting clay, silt, sand, pH, and TC with high accuracy for soils developed in loess, and that spectral models should be developed for different horizons to achieve high prediction accuracy.     

Prediction of soil organic matter using a spatially constrained local partial least squares regression and the Chinese vis–NIR spectral library

We need to determine the best use of soil vis–NIR spectral libraries that are being developed at regional, national and global scales to predict soil properties from new spectral readings. To reduce the complexity of a calibration dataset derived from the Chinese vis–NIR soil spectral library (CSSL), we tested a local regression method that combined geographical sub‐setting with a local partial least squares regression (local‐PLSR) that uses a limited number of similar vis–NIR spectra (k‐nearest neighbours). The central idea of the local regression, and of other local statistical approaches, is to derive a local prediction model by identifying samples in the calibration dataset that are similar, in spectral variable space, to the samples used for prediction. Here, to derive our local regressions we used Euclidean distance in spectral space between the calibration dataset and prediction samples, and we also used soil geographical zoning to account for similarities in soil‐forming conditions. We tested this approach with the CSSL, which comprised 2732 soil samples collected from 20 provinces in the People's Republic of China to predict soil organic matter (SOM). Results showed that the prediction accuracy of our spatially constrained local‐PLSR method (R² = 0.74, RPIQ = 2.6) was better than that from local‐PLSR (R² = 0.69, RPIQ = 2.3) and PLSR alone (R² = 0.50, RPIQ = 1.5). The coupling of a local‐PLSR regression with soil geographical zoning can improve the accuracy of local SOM predictions using large, complex soil spectral libraries. The approach might be embedded into vis–NIR sensors for laboratory analysis or field estimation.