The role of topography, soil, and remotely sensed vegetation condition towards predicting crop yield

Abstract

Foreknowledge of the spatiotemporal drivers of crop yield would provide a valuable source of information to optimize on-farm inputs and maximize profitability. In recent years, an abundance of spatial data providing information on soils, topography, and vegetation condition have become available from both proximal and remote sensing platforms. Given the wide range of data costs (between USD $0−50/ha), it is important to understand where often limited financial resources should be directed to optimize field production. Two key questions arise. First, will these data actually aid in better fine-resolution yield prediction to help optimize crop management and farm economics? Second, what level of priority should stakeholders commit to in order to obtain these data? Before fully addressing these questions a remaining challenge is the complex nature of spatiotemporal yield variation. Here, a methodological framework is presented to separate the spatial and temporal components of crop yield variation at the subfield level. The framework can also be used to quantify the benefits of different data types on the predicted crop yield as well to better understand the connection of that data to underlying mechanisms controlling yield. Here, fine-resolution (10 m) datasets were assembled for eight 64 ha field sites, spanning a range of climatic, topographic, and soil conditions across Nebraska. Using Empirical Orthogonal Function (EOF) analysis, we found the first axis of variation contained 60-85 % of the explained variance from any particular field, thus greatly reducing the dimensionality of the problem. Using Multiple Linear Regression (MLR) and Random Forest (RF) approaches, we quantified that location within the field had the largest relative importance for modeling crop yield patterns. Secondary factors included a combination of vegetation condition, soil water content, and topography. With respect to predicting spatiotemporal crop yield patterns, we found the RF approach (prediction RMSE of 0.2−0.4 Mg/ha for maize) was superior to MLR (0.3−0.8 Mg/ha). While not directly comparable to MLR and RF the EOF approach had relatively low error (0.5-1.7 Mg/ha) and is intriguing as it requires few calibration parameters (2-6 used here) and utilizes the climate-based aridity index, allowing for pragmatic long-term predictions of subfield crop yield.

CubeSats deliver new insights into agricultural water use at daily and 3 m resolutions

“…Since the irrigated fields received an additional water supply of 137.6 mm (US-Ne1) and 123.2 mm (US-Ne2), respectively from irrigation (see Table 1), the field variability may also reflect the underlying soil composition of the fields. Differences in nutrient amount and soil matrix structure have also been linked to crop yields at these sites 53 . On the other hand, the cumulative CubeSat E of the rainfed US-Ne3 site was higher than the cumulative precipitation amounts for the period August 19 until September 21 (35 days), which www.nature.com/scientificreports/ overlap with the sequence shown in the spatial maps of Fig.…”

Towards crop yield estimation at a finer spatial resolution using machine learning methods over agricultural regions

“…The triangular yellow markers mean RMSEs found that local scale models predicted yield more accurately than the region and state models. The variation of vegetation/climate conditions and other factors at different scales could be responsible for the discrepancies (Balaghi et al 2008;Franz et al 2020). Hence the improvement in yield estimation may be attributed to the finer grid level and the consideration of dynamic planting area, which provided more detailed and spatial representative data for yield estimation, especially in region A.…”

Analysis of Influencing Factors on Winter Wheat Yield Estimations Based on a Multisource Remote Sensing Data Fusion

“…RFR does not easily fall into overfitting and is more robust than other methods in terms of noise due to the introduction of randomness. Many studies have shown that the RFR method has good applicability in crop yield estimations (Breiman, 2001;Alberto et al, 2014;Franz et al, 2020).…”