Raster dataset showing the probability of detecting atrazine/desethyl-atrazine in ground water in Colorado, hydrogeomorphic regions not included and atrazine use estimates included.

This dataset is one of eight datasets produced by this study.
Four of the datasets predict the probability of detecting
atrazine and(or) desethyl-atrazine (a breakdown product of atrazine)
in ground water in Colorado; the other four predict the probability
of detecting elevated concentrations of nitrate in ground water in
Colorado. The four datasets that predict the probability of
atrazine and(or) desethyl-atrazine (atrazine/DEA) are differentiated
by whether or not they incorporated atrazine use and whether
or not they incorporated hydrogeomorphic regions. The four datasets
that predict the probability of elevated concentrations of nitrate
are differentiated by whether or not they incorporated fertilizer
use and whether or not they incorporated hydrogeomorphic
regions. Each of the eight datasets has its own unique strengths
and weaknesses. The user is cautioned to read Rupert (2003, Probability
of detecting atrazine/desethyl-atrazine and elevated concentrations
of nitrate in ground water in Colorado: U.S. Geological Survey
Water-Resources Investigations Report 02-4269, 35 p.,
https://water.usgs.gov/pubs/wri/wri02-4269/) to determine if he(she)
is using the most appropriate dataset for his(her) particular needs.
This dataset specifically predicts the probability of detecting
atrazine/DEA in ground water in Colorado with hydrogeomorphic
regions not included and atrazine use estimates included. The
following text was extracted from Rupert (2003).

Draft Federal regulations may require that each State develop a
State Pesticide Management Plan for the herbicides atrazine,
alachlor, metolachlor, and simazine. Maps were developed that the
State of Colorado could use to predict the probability of detecting
atrazine/DEA in ground water in Colorado. These maps can be
incorporated into the State Pesticide Management Plan and can help
provide a sound hydrogeologic basis for atrazine management in
Colorado. Maps showing the probability of detecting elevated nitrite
plus nitrate as nitrogen (nitrate) concentrations in ground water in
Colorado also were developed because nitrate is a contaminant of
concern in many areas of Colorado.

Maps showing the probability of detecting atrazine/DEA at or greater
than concentrations of 0.1 microgram per liter and nitrate
concentrations in ground water greater than 5 milligrams per liter
were developed as follows: (1) Ground-water quality data were overlaid
with anthropogenic and hydrogeologic data by using a geographic
information system (GIS) to produce a dataset in which each well had
corresponding data on atrazine use, fertilizer use, geology,
hydrogeomorphic regions, land cover, precipitation, soils, and well
construction. These data then were downloaded to a statistical
software package for analysis by logistic regression. (2) Relations
were observed between ground-water quality and the percentage of
land-cover categories within circular regions (buffers) around wells.
Several buffer sizes were evaluated; the buffer size that provided
the strongest relation was selected for use in the logistic regression
models. (3) Relations between concentrations of atrazine/DEA and
nitrate in ground water and atrazine use, fertilizer use, geology,
hydrogeomorphic regions, land cover, precipitation, soils, and
well-construction data were evaluated, and several preliminary
multivariate models with various combinations of independent variables
were constructed. (4) The multivariate models that best predicted
the presence of atrazine/DEA and elevated concentrations of nitrate
in ground water were selected. (5) The accuracy of the multivariate
models was confirmed by validating the models with an independent
set of ground-water quality data. (6) The multivariate models were
entered into a geographic information system and the probability
GRIDS were constructed.

本数据集为本研究生成的8套数据集之一。其中4套数据集用于预测美国科罗拉多州地下水中检出莠去津（atrazine）及其代谢产物脱乙基莠去津（desethyl-atrazine，以下简称DEA）的概率；另外4套则用于预测该地区地下水中硝酸盐浓度超标的概率。预测莠去津/DEA检出概率的4套数据集，依据是否纳入莠去津使用量数据、是否纳入水文地貌区域数据进行区分；预测硝酸盐浓度超标概率的4套数据集，则依据是否纳入化肥使用量数据、是否纳入水文地貌区域数据进行区分。8套数据集各有其独特的优势与局限，提醒使用者需参考Rupert（2003年，《美国科罗拉多州地下水中莠去津/脱乙基莠去津及硝酸盐浓度超标检出概率》，美国地质调查局水资源调查报告02-4269，共35页，https://water.usgs.gov/pubs/wri/wri02-4269/）的内容，以判断所选数据集是否适配自身特定需求。
本数据集特指在未纳入水文地貌区域数据、但纳入莠去津使用量估算数据的前提下，预测美国科罗拉多州地下水中莠去津/DEA检出概率的数据集。以下内容节选自Rupert（2003年）的报告：
美国联邦法规草案可能要求各州针对莠去津、甲草胺（alachlor）、异丙甲草胺（metolachlor）及西玛津（simazine）这四种除草剂制定州级农药管理计划。科罗拉多州据此开发了可用于预测本州地下水中莠去津/DEA检出概率的专题地图，该类地图可纳入州级农药管理计划，为科罗拉多州的莠去津管理提供可靠的水文地质依据。同时，鉴于硝酸盐是科罗拉多州诸多区域的关注污染物，研究团队还开发了可预测该州地下水中亚硝酸盐与硝酸盐（以氮计）浓度超标的专题地图。
针对莠去津/DEA浓度≥0.1微克/升、硝酸盐浓度＞5毫克/升的检出概率专题地图，开发流程如下：
1. 借助地理信息系统（Geographic Information System, GIS）将地下水水质数据与人为活动数据、水文地质数据进行叠加，生成包含每一口监测井对应数据的数据集，涵盖莠去津使用量、化肥使用量、地质条件、水文地貌区域、土地覆被、降水量、土壤类型及井体结构等信息。随后将该数据集导入统计软件包，通过逻辑回归开展分析。
2. 分析地下水质与监测井周边圆形区域（缓冲区）内各类土地覆被占比之间的关联，对多种缓冲区尺寸进行评估，选取与水质关联度最强的尺寸用于逻辑回归模型。
3. 评估地下水中莠去津/DEA、硝酸盐浓度与莠去津使用量、化肥使用量、地质条件、水文地貌区域、土地覆被、降水量、土壤类型及井体结构数据之间的关联，并构建多个包含不同自变量组合的初步多元回归模型。
4. 选取能够最优预测地下水中莠去津/DEA检出情况及硝酸盐浓度超标的多元回归模型。
5. 通过独立地下水水质数据集对模型进行验证，确认多元回归模型的准确性。
6. 将经过验证的多元回归模型导入地理信息系统，生成概率栅格（GRIDS）。