Ielpo Pierina, Leardi Riccardo, Pappagallo Giuseppe, Uricchio Vito Felice
Water Research Institute, National Research Council, Viale de Blasio 5, 70132, Bari, Italy.
Institute of Atmospheric Sciences and Climate, National Research Council, s.p. Lecce-Monteroni Km 1.2, 73100, Lecce, Italy.
Environ Sci Pollut Res Int. 2017 Jun;24(16):13967-13978. doi: 10.1007/s11356-016-7944-y. Epub 2016 Oct 29.
In this paper, the results obtained from multivariate statistical techniques such as PCA (Principal component analysis) and LDA (Linear discriminant analysis) applied to a wide soil data set are presented. The results have been compared with those obtained on a groundwater data set, whose samples were collected together with soil ones, within the project "Improvement of the Regional Agro-meteorological Monitoring Network (2004-2007)". LDA, applied to soil data, has allowed to distinguish the geographical origin of the sample from either one of the two macroaeras: Bari and Foggia provinces vs Brindisi, Lecce e Taranto provinces, with a percentage of correct prediction in cross validation of 87%. In the case of the groundwater data set, the best classification was obtained when the samples were grouped into three macroareas: Foggia province, Bari province and Brindisi, Lecce and Taranto provinces, by reaching a percentage of correct predictions in cross validation of 84%. The obtained information can be very useful in supporting soil and water resource management, such as the reduction of water consumption and the reduction of energy and chemical (nutrients and pesticides) inputs in agriculture.
本文介绍了将主成分分析（PCA）和线性判别分析（LDA）等多元统计技术应用于广泛土壤数据集所获得的结果。这些结果与在“区域农业气象监测网络改进项目（2004 - 2007）”中与土壤样本一起采集的地下水数据集所获得的结果进行了比较。将LDA应用于土壤数据，可以从两个大区中的任何一个区分样本的地理来源：巴里省和福贾省与布林迪西省、莱切省和塔兰托省，交叉验证中的正确预测百分比为87%。在地下水数据集的情况下，当样本被分为三个大区：福贾省、巴里省以及布林迪西省、莱切省和塔兰托省时，获得了最佳分类，交叉验证中的正确预测百分比达到了84%。所获得的信息对于支持土壤和水资源管理非常有用，例如减少农业用水以及减少能源和化学物质（养分和农药）投入。
