ABSTRACT

Precision agriculture manages within-field spatial variability by applying suitable inputs at the appropriate time, place, and amount. Delineation of field-specific management zones (MZs), representing significantly different yield potentials prescribe the rates of a specific crop inputs within-field. This paper examines multiple-year maize grain yield maps (2014, 2015, 2017 and 2018) and their spatial and temporal variability of within-field datasets (soil electrical conductivity [EC], soil organic matter [OM], and elevation) and climate data. The research was undertaken on a non-irrigated field at New Zealand’s Foundation for Arable Research (FAR) in the Waikato region, to provide a simple, heuristic method to delineate dynamic MZs for crop inputs. Supervised statistical learning models (stepwise multiple linear regression [SMLR], feedforward neural network (FFNN), classification and regression tree (CART), random forest (RF), extreme gradient boosting (XGBoost) and Cubist regression) were implemented to predict spatial yield. Prediction accuracies of the trained models were evaluated by withholding one subset of data for testing. For internal ‘split-sample' validation, CART, random forest and XGBoost produced slightly better statistical predictions (RMSE = 1.9–2.0 and R² = 0.60–0.63) than Cubist and FFNN (RMSE = 2.1–2.2 and R² = 0.52–0.57), whereas MLR produced the weakest prediction (RMSE = 2.3 and R² = 0.51). Spatial yield prediction of individual years, were poor (R² = 0.07–0.36). Input data used is readily and inexpensive for small arable fields in New Zealand. The methods presented, could be applied to a wider range of arable crops for within-field management inputs, to respond to spatially diverse soil texture distribution and variable rainfall patterns.

抽象的

精准农业通过在适当的时间，地点和数量应用适当的输入来管理田间空间变异性。田间特定管理区（MZ）的划分代表了明显不同的单产潜力，规定了田间特定作物投入的比率。本文研究了多年玉米谷物产量图（2014年，2015年，2017年和2018年）及其田间数据集（土壤电导率[EC]，土壤有机质[OM]和海拔）和气候的时空变化数据。这项研究是在怀卡托地区的新西兰耕地研究基金会（FAR）的非灌溉领域进行的，目的是提供一种简单的启发式方法来勾勒出作物投入的动态MZ。监督统计学习模型（逐步多元线性回归[SMLR]，前馈神经网络（FFNN），分类和回归树（CART），随机森林（RF），极端梯度增强（XGBoost）和Cubist回归被用来预测空间产量。通过保留一个数据子集进行测试，可以评估经过训练的模型的预测准确性。对于内部“分割样本”验证，CART，随机森林和XGBoost产生了更好的统计预测（RMSE = 1.9–2.0和R ²  = 0.60–0.63）高于Cubist和FFNN（RMSE = 2.1–2.2，R ²  = 0.52–0.57），而MLR得出的预测最弱（RMSE = 2.3，R ²  = 0.51）。个别年份的空间产量预测很差（R ²  = 0.07–0.36）。对于新西兰的小耕地来说，使用的输入数据既便宜又便宜。提出的方法可应用于范围更广的耕作作物，以进行田间管理投入，以应对空间上多样化的土壤质地分布和变化的降雨模式。