共查询到20条相似文献，搜索用时 218 毫秒
1.
三峡库区紫色砂岩不同发育程度土壤入渗特征及其影响因素 总被引：1，自引：1，他引：0
为探究典型母岩不同发育程度土壤入渗特征,在三峡库区王家桥小流域采用圆盘入渗仪测定新成土（S1）、雏形土（S2）、淋溶土（S3）3种紫色砂岩不同发育程度土壤入渗过程,探究入渗过程的影响因素,并用3种常用模型进行入渗过程模拟,分析比较这些模型的适宜性。结果表明：（1）不同发育程度间土壤理化性质差异显著。雏形土和淋溶土土壤容重较新成土分别增加10.71%,19.50%,土壤总孔隙度分别降低8.79%,18.69%,通气孔隙度分别降低67.40%,8.16%,土壤黏粒含量分别增加10.01%,38.36%,砂粒含量分别减小8.09%,48.29%,土壤有机质分别增加2.88%,8.68%。（2）不同发育程度土壤间初始入渗率、平均入渗率、饱和导水率均表现为新成土>雏形土>淋溶土,雏形土、淋溶土平均入渗率及饱和导水率分别是新成土的0.99,0.58和0.89,0.83倍。（3）不同发育程度土壤理化性质差异对土壤入渗具有显著影响,土壤入渗速率与总孔隙度、毛管孔隙度、通气孔隙度、砂粒含量呈正相关关系,与容重、黏粒含量、有机质含量呈负相关关系。（4） Horton模型对紫色砂岩不同发育程度土壤入渗过程拟合效果最优（R2=0.942）,Kostiakov模型次之（R2=0.858）,Philip模型拟合效果较差（R2=0.832）。通过观测与模拟不同发育程度土壤入渗过程,研究结果可为流域土壤水分运移规律探究提供有益借鉴。 相似文献
2.
为探究黄淮海旱作区耕层土壤质量特征,基于土壤物理、化学及剖面特征,建立黄淮海旱作区耕层土壤质量评价指标体系,运用主成分分析法构建耕层质量评价指标的最小数据集（minimum data set,MDS）,结合障碍因子诊断模型揭示黄淮海旱作区耕层土壤质量特征及其障碍因素。结果表明：1）研究区耕层土壤质量评价最小数据集由土壤有机质、土壤阳离子交换量、土壤pH、耕作层厚度、耕作层穿透阻力和耕作层压实度构成,基于最小数据集和全指标数据集的耕层土壤质量指数间显著正相关（R2=0.61,P＜0.05）,Nash有效系数和相对偏差系数分别为0.601和0.181,表明最小数据集的指标能够代替全部数据集指标对黄淮海旱作区耕层质量进行评价;2）研究区耕层土壤质量总体处于中等水平,质量指数为0.25～0.61;适宜耕层各项指标如下：耕作层厚度不小于17.20 cm,耕作层穿透阻力不大于896.10 kPa,耕作层土壤压实度不大于78.01%,pH值为8.01～9.37,有机质不小于17.87 g/kg,阳离子交换量不小于21.13 cmol/kg;3）黄淮海旱作区存在明显的障碍类型,耕层障碍可分为薄化紧实与养分贫瘠障碍耕层、养分贫瘠耕层、土壤紧实型耕层3类。其中有机质含量低、阳离子交换量低、耕作层压实度过高是黄淮海旱作区耕层质量主要障碍。研究为黄淮海旱作区耕层土壤质量提升和改善提供理论支撑。 相似文献
3.
中性水稻土中的铁解及其影响 总被引：1，自引：0，他引：1
我们曾发现,苏州地区的某些水稻土的耕层土壤,pH值可低至5.0-5.5,有些土壤的交换性Ca/Mg比值亦明显下降[2,3]。黄棕壤在添加有机物质并淹水培育后,使其交换性镁含量增加和交换性钙含量下降[1],而试样的pH值与交换性钙镁总量之间,出现显著的正相关(r=0.837,n=10)。 相似文献
4.
为揭示粗颗粒土壤坡面侵蚀机理,采用湖北通城县、江西赣县、福建长汀县、广东五华县4个样地的4种粗颗粒土壤（分别定义为TCA、GXA、CTA、WHA）进行室内模拟降雨试验,研究粗颗粒土壤坡面侵蚀过程及侵蚀泥沙颗粒组成的变化规律。结果表明：（1）4种土壤的地表径流随着降雨时间的增长呈现出先增加后递减并趋于稳定的规律;（2）4种土壤的侵蚀特征存在差异,土壤侵蚀速率表现为WHA>TCA>GXA>CTA;（3）4种土壤的侵蚀泥沙中颗粒分布百分比大小均为砂粒>黏粒>粉粒>砾石。不同土壤侵蚀泥沙富集率表现出明显差异;（4）水流功率与土壤侵蚀速率的相关性显著,用幂函数可以准确描述其关系。在表达式中引入土壤黏粒含量、砾石含量后模型更加可靠（Dr=0.001ω1.163Cl-4.069,R2=0.82;Dr=0.003ω1.149Gr-1.934,R2=0.84）,提高了模型预测土壤侵蚀速率的精度,在实际应用中具有更广的适应范围与现实价值。 相似文献
5.
耕作方式对辽西褐土区土壤穿透阻力的影响及机理 总被引：2，自引：2，他引：0
为了探明耕作方式转变对土壤物理性质的影响，研究设置田间定位试验，监测长期旋耕转变为免耕和深松耕后土壤容重、水分和穿透阻力的变化特征。试验设免耕（no tillage，NT）、深松（subsoiling，SS）、旋耕（rotary tillage，RT）3个处理，在玉米生长季监测土壤含水量、容重和穿透阻力动态，定量并分析土壤穿透阻力对含水量和容重变化的响应。结果表明，玉米生育期NT处理的土壤容重保持相对稳定，RT和SS处理容重逐渐增大；与RT和SS处理相比，NT处理增加0—30 cm的容重、0—45 cm的含水量和0—15 cm的穿透阻力，但在干旱时期降低15—45 cm的穿透阻力，避免了土壤紧实对玉米的胁迫。基于含水量和容重参数，建立了预测土壤穿透阻力的指数模型，其P<0.001，R2为0.77。模型结果表明，当容重>1.4 g/cm3且含水量<0.13 cm3/cm3时，土壤穿透阻力将大于限制作物生长的阈值（2 MPa）；在含水量<0.2 cm3/cm3时，土壤穿透阻力对含水量的敏感性显著高于容重，说明该区域干旱（水分）引起的土壤紧实度增加比压实更为重要。免耕有助于该区域保持土壤水分，同时降低容重增加导致的土壤紧实效应，有利于避免土壤紧实胁迫对作物生长的影响。 相似文献
6.
黄土高原典型退耕草地植被特征对土壤入渗过程的影响 总被引：1，自引：1，他引：0
植被恢复过程可显著影响土壤入渗性能。通过选取黄土高原典型草地白羊草和铁杆蒿草地,设置不同种植密度（5,10,15,20,25,30株/m2）和采用人工模拟降雨试验（60 mm/h,60 min）,系统研究了草地植被特征对土壤入渗过程的影响。结果表明：（1）种植密度增加可显著延缓产流,不同种植密度下白羊草草地和铁杆蒿草地初始产流时间分别为0.76~5.74,0.87~2.08 s,且随盖度、根系生物量和有机质的增加呈幂函数增加（R2≥0.18,p<0.05）。（2）不同种植密度下白羊草草地的平均入渗速率、稳定入渗速率、入渗总量分别为0.47~0.82,0.46~0.82 mm/min和7.12~11.84 mm,铁杆蒿草地分别为0.38~0.67,0.35~0.60 mm/min和5.70~10.07 mm。当种植密度为20株/m2时,土壤入渗各参数均最大;平均入渗速率、稳定入渗速率、入渗量总量、入渗系数（K）随土壤有机质的提高呈幂函数增大（R2≥0.26,p<0.01）,衰减系数（α）随生物结皮盖度呈降低趋势（p>0.05）。（3）白羊草草地具有较高的根系生物量、生物结皮盖度和有机质含量,其初始产流时间、平均入渗速率、稳定入渗速率、入渗量总量及入渗系数（K）均不同程度高于铁杆蒿草地,衰减系数（α）低于铁杆蒿草地,土壤入渗性能较强。总体而言,对于典型退耕草地,土壤入渗总量（A）可表征为根系生物量密度（RMD）和土壤有机质（SOC）的拟合函数（A=2.77×RMD0.149 SOC0.614,R2=0.663,NSE=0.653）。研究结果可为黄土高原退耕草地生态水文过程和植被建设提供数据来源和理论依据。 相似文献
7.
以甘肃白银某污灌区重金属污染农田土壤为研究对象，对影响高精度便携式X荧光光谱（HDXRF）法总镉（CdT）测定精度的主要因素进行了筛选，分别研究了土壤水分、有机质类型与含量、土壤类型对HDXRF法CdT测定的影响，并采用相对误差（RE）、相对标准偏差（RSD）和决定系数（R2）对测定结果的准确度和精密度进行了评价。结果表明：HDXRF法CdT测定的RE≤10%、RSD≤10%、R2>0.99，符合农田土壤环境质量监测技术规范和美国环境保护署标准的准确度和精密度规定。HDXRF法CdT测定结果随着土壤水分含量的增加呈指数衰减趋势，衰减方程为y=0.803e–1.3284x，衰减系数（μω）为–1.328 4，R2为0.984 5。HDXRF法CdT测定结果与有机质含量呈显著的负相关关系（r=–0.955），且腐殖酸（HA）比泥炭（Peat）对测定结果的影响更大，HA与测定结果的校正方程为y=–1.555x +0.780，R2为0.934 4。土壤类型对HDXRF法CdT测定结果存在一定的影响，相对于红壤和水稻土，灰钙土的测定结果与传统实验室分析方法测定结果更接近。总之，虽然HDXRF法CdT测定结果受多种因素影响，但通过校正模型校正，其校正结果的可靠性能够满足Cd污染农田土壤精准调查需求。 相似文献
8.
基于133个滨海湿地土样的全氮（TN）含量和光谱反射率（R）及其对数（lgR）、对数的一阶微分（（lgR）''）、倒数（1/R）、倒数的一阶微分（（1/R）''）、一阶微分（R''）、平方根（√R）、一阶微分的倒数（1/（R）''）变换，采用偏最小二乘回归（PLSR）、随机森林回归（RFR）和支持向量机回归（SVR）3种算法分别建立土壤TN含量估测模型。结果表明：①土壤TN含量与光谱变换形式相关性由高到低为：（1/R）''> R''> （lgR）''> 1/R > lgR > 1/（R）''> √R > > R，经光谱变换，土壤TN含量与变换光谱的相关性均高于R，其中与（1/R）''的Pearson相关系数最大为0.746。②PLSR和SVR基于R''、（1/R）''、（lgR）''和1/（R）''变换构建的模型、RFR方法构建的所有模型R2均大于0.732，均可用于滨海湿地土壤TN含量的估算。③基于1/（R）''建立的SVR模型预测精度最高，其R2为0.987，RMSE为0.057 g/kg，MAE为0.050 g/kg，是预测滨海湿地土壤TN含量的最优模型，可为准确获取滨海湿地土壤TN含量提供稳定方法。 相似文献
9.
及时并准确地估计作物产量，对保障粮食安全、维护世界粮食供应稳定具有重要意义。此前，已有许多研究者使用机器学习方法对作物产量预估进行研究。然而，结合作物的空间分布、使用局部模型进行分析的研究较少；且诸多研究均以年份为时间尺度进行建模，未能精细到作物生长的各个阶段，无法实现作物产量的早期预测。针对以上问题，该研究结合多源遥感数据，利用随机森林（random forest，RF）以及地理加权随机森林（geographically weighted random forest regression，GWRFR）模型对美国县级玉米产量进行建模，探讨全局与局部模型在玉米产量预测方面的性能；并通过将GWRFR模型应用于玉米的各个物候期，获取了玉米产量的最佳提前预测时间。结果表明，GWRFR局部模型的精度（R2=0.87，RMSE=864.21 kg/hm2）高于传统的RF全局模型（R2=0.83，RMSE=994.75 kg/hm2），并且能够较好地克服空间数据的非平稳性，即使在全局模型中加入经纬度作为变量，RF模型的预测效果（R2=0.85，RMSE=890.88 kg/hm2）仍然低于GWRFR模型。对于玉米产量的预测可以提前至收获前2～3个月，即在乳熟期前后就能得到比较准确的预测结果（R2=0.90，RMSE=748.39 kg/hm2）。该研究结果可为大尺度作物产量预估提供一种新的思路，对区域或全球其他作物的产量预测也具有一定的指导意义。 相似文献
10.
基于遥感数据、气象数据等,利用RWEQ模型和风蚀预报模型对内蒙古自治区2000—2017年土壤风蚀进行评估并分析其驱动因素。结果表明：（1） RWEQ模型（R2=0.85,P<0.01）和风蚀预报模型（R2=0.43,P<0.01）的预测值与137Cs示踪技术风蚀的值具有较好的相关性,其中RWEQ模型预测精度更好。（2）时间上,RWEQ和风蚀预报模型模拟的结果均表明2000—2017年内蒙古自治区土壤风蚀呈下降的趋势,下降趋势分别为0.73,1.18 t/（hm2·a）,2个模型模拟的土壤风蚀模数在2011年均达到最低值。空间上,2000—2017年,2个模型的模拟结果均表明内蒙古自治区土壤风蚀以微度和轻度侵蚀为主,其中剧烈侵蚀在整个研究区的占比较小（RWEQ 1.79%,风蚀预报模型5.45%）,主要分布于北方风沙区的西南部。趋势上,89.74%（RWEQ）和72.05%（风蚀预报模型）的土壤风蚀模数呈下降趋势,其中显著降低的区域主要分布于北方风沙区的巴丹吉林沙漠和乌兰布和沙漠。（3）大风天数对土壤风蚀具有显著影响,随着大风天数的增多,土壤风蚀呈显著上升趋势,植被覆盖度和降水量的增长在一定程度上可抑制土壤风蚀的进程。 相似文献
11.
稻米镉的生物富集系数与其影响因素的量化关系 总被引：1，自引：1，他引：1
为进一步明确田间环境中稻米镉的生物富集系数(BCF)与其影响因素的定量关系,以原农业部环境监测总站对我国南方水稻产地的例行监测数据为基础,系统分析了土壤有效镉、pH、土壤有机质(SOM)及阳离子交换量(CEC)与稻米镉BCF的相关关系,并通过多元线性回归构建了二者间的定量关系模型。结果表明:研究区域土壤全镉范围为0.25～10.34 mg/kg,平均值为1.94 mg/kg,是我国《土壤环境质量农用地土壤污染风险管控标准(试行)》(GB15618—2018)中镉污染风险筛选值(0.4 mg/kg)的4.85倍;简单线性相关分析表明,稻米镉的BCF与土壤有效镉和SOM呈极显著正相关(P0.01),相关系数分别为0.395和0.474,与p H呈极显著负相关(P0.01),相关系数为–0.470,与CEC呈显著负相关(P0.05),相关系数为–0.200;通过多元线性回归得到土壤有效镉、pH和SOM构建的三因子量化关系模型lgBCF=–0.346pH+0.013lgSOM+0.181lgCdavailable+2.001(R2=0.560,P0.01,n=112)达到了极显著水平,能较好预测我国南方水稻产地稻米镉含量及土壤镉的生态安全阈值。 相似文献
12.
《植物养料与土壤学杂志》2017,180(3):366-380
Paddy soil management is generally thought to promote the accumulation of soil organic matter (SOM) and specifically lignin. Lignin is considered particularly susceptible to accumulation under these circumstances because of the recalcitrance of its aromatic structure to biodegradation under anaerobic conditions (i.e ., during inundation of paddy fields). The present study investigates the effect of paddy soil management on SOM composition in comparison to nearby agricultural soils that are not used for rice production (non‐paddy soils). Soil types typically used for rice cultivation were selected, including Alisol, Andosol and Vertisol sites in Indonesia (humid tropical climate of Java) and an Alisol site in China (humid subtropical climate, Jiangxi province). These soil types represent a range of soil properties to be expected in Asian paddy fields. All upper‐most A horizons were analysed for their SOM composition by solid‐state 13C nuclear magnetic resonance (NMR) spectroscopy and for lignin‐derived phenols by the CuO oxidation method. The SOM composition was similar for all of the above named parent soil types (non‐paddy soils) and was also not affected by paddy soil management. A substantial proportion (up to 23%) of the total aryl‐carbon in some paddy and non‐paddy soils was found to originate from condensed aromatic‐carbon (e.g ., charcoal). This may be attributed to the burning of crop residues. On average, the proportion of lignin was low and made up 20% of the total SOM, and showed no differences between straw, particulate organic matter (POM), and the bulk soil material. The results from CuO oxidation are consistent with the data obtained from solid‐state 13C NMR spectroscopy. The extraction of lignin‐derived phenols revealed low VSC (vanillyl, syringyl, cinnamyl) values for all investigated soils in a range (4 to 12 g kg−1 OC) that was typical for agricultural soils. In comparison to adjacent non‐paddy soils, the data do not provide evidence for a substantial accumulation of phenolic lignin‐derived structures in the paddy soils, even for those characterized by higher organic carbon (OC) contents (e.g ., Andosol‐ and Alisol (China)‐derived paddy soils). We conclude that the properties of the parent soil types are more important for the lignin content of the soils than the effect of paddy management itself. 相似文献
13.
Soil organic matter (SOM) is important for plant growth and production. Conventional analyses of SOM are expensive and time consuming. Hyperspectral remote sensing is an alternative approach for SOM estimation. In this study, the diffuse reflectance spectra of soil samples from Qixia City, the Shandong Peninsula, China, were measured with an ASD FieldSpec 3 portable object spectrometer (Analytical Spectral Devices Inc., Boulder, USA). Raw spectral reflectance data were transformed using four methods:nine points weighted moving average (NWMA), NWMA with first derivative (NWMA + FD), NWMA with standard normal variate (NWMA + SNV), and NWMA with min-max standardization (NWMA + MS). These data were analyzed and correlated with SOM content. The evaluation model was established using support vector machine regression (SVM) with sensitive wavelengths. The results showed that NWMA + FD was the best of the four pretreatment methods. The sensitive wavelengths based on NWMA + FD were 917, 991, 1 007, 1 996, and 2 267 nm. The SVM model established with the above-mentioned five sensitive wavelengths was significant (R2=0.875, root mean square error (RMSE)=0.107 g kg-1 for calibration set; R2=0.853, RMSE=0.097 g kg-1 for validation set). The results indicate that hyperspectral remote sensing can quickly and accurately predict SOM content in the brown forest soil areas of the Shandong Peninsula. This is a novel approach for rapid monitoring and accurate diagnosis of brown forest soil nutrients. 相似文献
14.
AbstractTo evaluate labile selenium (Se) content in agricultural soils in Japan and to investigate its determining factors, 178 soil samples were collected from the surface layer of paddy or upland fields in Japan and their soluble Se contents were determined. Two grams of soil was extracted with 20 mL of 0.1 mol L?1 sodium sulfate (Na2SO4) solution for 30 min in boiling water, and the released Se was reduced to Se (IV) after organic matter decomposition. The concentration of Se (IV) was then determined by high performance liquid chromatography (HPLC) with a fluorescence detector after treatment with 2,3-diaminonaphthalene (DAN) and extraction with cyclohexane. Soluble Se content ranged from 2.5 to 44.5 μg kg?1 with geometric and arithmetic means of 11.4 and 12.8 μg kg?1, respectively, and corresponded to 3.2% of the total Se on average. The overall data showed log-normal distribution. In terms of soil type, Non-allophanic Andosols and Volcanogenous Regosols had relatively high soluble Se content, and Wet Andosols and Lowland Paddy soils had relatively low soluble Se content. In terms of land use, upland soils had significantly higher soluble Se content than paddy soils (p < 0.01). The soluble Se content had significant positive correlation with total organic carbon (TOC) content of the extract, soil pH and total Se content (p < 0.01). In conclusion, total Se content in combination with soil pH was the main determining factor of the soluble Se content of agricultural soils in Japan. 相似文献
15.
16.
Changes in soil pH and phosphorus availability during decomposition of cover crop residues 总被引：1，自引：0，他引：1
Juan I. Vanzolini Juan A. Galantini Juan M. Martínez 《Archives of Agronomy and Soil Science》2017,63(13):1864-1874
The aim of this study was to determine the effect of winter cover crop (CC) residues on soil pH and phosphorus (P) availability. Three incubation assays were performed in pots using two CC: vetch (V) (Vicia villosa Roth.) and oats (Oa) (Avena sativa L.). Soil samples were taken from 10 sites at 0–20-cm depth. The rate of residues were 0 (D0), 10 (D1), 20 (D2), 30 (D3), and 40 (D4) g dry matter kg?1 soil and the soil sampling was after 10, 20, 30, 60, 90, and 120 days of incubation. Soil pH, extractable P (Pe), and soil organic matter (SOM) and its fractions were determined. The pH increase was correlated with the rate applied (D1 < D2 < D3 < D4). No differences were found for pH comparing V and Oa residues with low residue rates. Soil pH changes were dependent from initial pH and SOM fractions in different soils across the incubation period. The multiple regression models showed that the pH changes were dependent on initial pH level and SOM fractions with a high R2 (0.81). CC residues and its quantities produced different changes on pH – especially at the beginning of the incubation – which influenced the P availability. 相似文献
17.
Regression models for predicting soil bulk density (BD) have usually been related to organic matter content,but it remains unknown whether soil acidity modifies this relationship,particularly for afforested/reforested soils.We measured soil BD along with organic matter content and pH in an afforested/reforested area in Northwest and Northeast China.Using these measurements,we parameterized and validated three BD models:the Adams equation,and exponential and radical models.Model validation showed that the Adams equation failed to predict the BD of the afforested/reforested soils,producing a large overestimation.Incorporation of soil pH into the Adams equation significantly improved its performance.The exponential and radical models parameterized by the measured data simulated soil BD quite well,particularly when soil pH was incorporated.However,incorporation of soil texture variables into these models did not improve model performance compared with the pH-modified models.This led to the conclusion that the Adams equation,exponential,and radical models with pH modification are applicable to afforested/reforested soils with various acidities. 相似文献
18.
生物质炭添加对重金属污染稻田土壤理化性状及微生物量的影响 总被引：2，自引：1，他引：1
分析了生物质炭添加对红壤性水稻土理化性状、重金属含量及微生物生物量的影响。通过田间小区长期定位试验,一次性施入不同量生物质炭(0,10,20,30,40t/hm2),于2017年9月采集各处理表层土样(0—15cm),研究土壤理化性状、重金属含量及微生物生物量的变化。结果表明:生物质炭添加对土壤理化性状、重金属含量及微生物生物量均有显著影响。与对照相比,供试土壤的pH、EC和有机质含量随生物质炭添加量的增加而增大,增幅分别为5.11%~18.43%,37.62%~104.31%和1.72%~22.41%,而有效磷和铵态氮含量随生物质炭添加量的增加呈先增大后减小趋势,分别在生物质炭添加量为10t/hm2和30t/hm2时达到最大值。随生物质炭添加量的增加,土壤有效态Cd和有效态Pb含量均呈降低趋势,而土壤有效态As含量呈先增加后减少的趋势,三者均在生物质炭添加量为40t/hm2时达到最小值。土壤微生物生物量碳、氮和微生物商随生物质炭添加量的增加均呈先升高后降低的趋势,均在生物质炭添加量为20t/hm2时达到最大值。相关分析表明,生物质炭添加量分别与土壤有效态Cd和Pb含量之间呈极显著负相关(P0.01);通径分析表明,生物质炭主要是通过直接作用影响土壤有效态Cd含量,而土壤pH、EC、有机质、微生物生物量碳、氮和有效磷主要是通过间接作用影响土壤有效态Cd含量。因此,添加适量生物质炭不仅可以改善土壤重金属污染现状和土壤理化性状,提高土壤养分含量,还可以改良土壤生物学性质,增加土壤微生物量。研究结果可为提高稻田土壤肥力和改善土壤重金属污染状况提供科学依据。 相似文献
19.
《Communications in Soil Science and Plant Analysis》2012,43(14):1753-1763
ABSTRACTPedotransfer functions (PTFs), as an indirect forecasting method, offer an alternative for labor-intensive bulk density (BD) measurements. In order to improve the forecasting accuracies, support vector machine (SVM) method was first used to develop PTFs for predicting BD. Cross-validation and grid-search methods were used to automatically determine the SVM parameters in the forecasting process. Soil texture and organic matter content were selected as input variables based on results of predecessors, coupled with gray correlation theory. And additional properties were added as inputs for improving PTF's accuracy and reliability. The performance of the PTF established by SVM method was compared with artificial neural network (ANN) method and published PTFs using two indexes: root-mean-square error (RMSE) and coefficient of determination(R2). Results showed that the average RMSE of published PTFs was 0.1053, and the R2 was 0.4558. The RMSE of ANN–PTF was 0.0638, and the R2 was 0.7235. The RMSE of SVM–PTF was 0.0558, and the R2 was 0.7658. Apparently, the SVM–PTF had better performance, followed by ANN–PTF. Additionally, performances could be improved when accumulated receiving water was added as predictor variable. Therefore, the first application of SVM data mining techniques in the prediction of soil BD was successful, improved the accuracy of predictions, and enhanced the function of soil PTFs. The idea of developing PTFs using SVM method for predicting soil BD in the study area could provide a reference for other areas. 相似文献
20.
Soil organic matter (SOM) plays a key role in soil, and is used to determine soil quality. Conventional soil property analysis is relatively slow, expensive and laborious. Although using a spectrometer can quickly assess a large amount of organic matter content, it is an expensive, complex and undefined process. This article presents a potential simple method for estimating black-SOM that uses a digital camera that is cheaper and easier to operate than a spectrometer. RGB (red, green and blue) image-intensity values of the soil from a digital camera were measured, to research the relationship between black-SOM and RGB. The results show the red image-intensity values provide the greatest correlation with SOM, with a correlation coefficient (r) reaching 0.73. A comparison with spectrometer results for SOM predictions shows that the best prediction result for the digital camera (R2 = 0.72, root-mean-square error [RMSE] = 0.40) is slightly better than the spectrometer (R2 = 0.65, RMSE = 0.45) at certain band points. Thus, a low-cost digital camera that is easy to operate can be used as an alternative tool for the rapid and accurate estimation of black-SOM content. 相似文献