Potato Yield Prediction Using Machine Learning Techniques and Sentinel 2 Data

Abstract

Traditional potato growth models evidence certain limitations, such as the cost of obtaining the input data required to run the models, the lack of spatial information in some instances, or the actual quality of input data. In order to address these issues, we develop a model to predict potato yield using satellite remote sensing. In an effort to offer a good predictive model that improves the state of the art on potato precision agriculture, we use images from the twin Sentinel 2 satellites (European Space Agency-Copernicus Programme) over three growing seasons, applying different machine learning models. First, we fitted nine machine learning algorithms with various pre-processing scenarios using variables from July, August and September based on the red, red-edge and infra-red bands of the spectrum. Second, we selected the best performing models and evaluated them against independent test data. Finally, we repeated the previous two steps using only variables corresponding to July and August. Our results showed that the feature selection step proved vital during data pre-processing in order to reduce multicollinearity among predictors. The Regression Quantile Lasso model (11.67% Root Mean Square Error, RMSE; R 2 = 0.88 and 9.18% Mean Absolute Error, MAE) and Leap Backwards model (10.94% RMSE, R 2 = 0.89 and 8.95% MAE) performed better when predictors with a correlation coefficient > 0.5 were removed from the dataset. In contrast, the Support Vector Machine Radial (svmRadial) performed better with no feature selection method (11.7% RMSE, R 2 = 0.93 and 8.64% MAE). In addition, we used a random forest model to predict potato yields in Castilla y León (Spain) 1-2 months prior to harvest, and obtained satisfactory results (11.16% RMSE, R 2 = 0.89 and 8.71% MAE). These results demonstrate the suitability of our models to predict potato yields in the region studied.The use of new technologies, such as satellite data, Geographic Information Systems (GIS) or Global Positioning Systems (GPS), can improve crop yield production and its quality [1], helping to secure food supply for the future as well as reducing the negative impacts resulting from agricultural practices [11]. More specifically, satellite remote sensing data has many applications in agriculture: soil property detection [12], crop type classification [13], crop yield forecast [14], crop health monitoring [15], soil moisture retrieval [16] or weather data assessment [17]. Remote sensing offers vast amounts of information which can be considered big data [18], and can help to improve crop modelling and decision-making. Big data has been described by Wolfert et al. [19] as "massive volumes of data with a wide variety that can be captured, analysed and used for decision-making", with said authors expecting big data to have a major impact on the agricultural sector. In order to improve the use of this data, given its size and variety, machine learning has emerged as an appropriate tool to identify rules and patterns in datasets [20], in addition to autonomously...

Non-Destructive Detection of Tea Leaf Chlorophyll Content Using Hyperspectral Reflectance and Machine Learning Algorithms

“…However, more suitable algorithms were found and kernel-based extreme learning machine (KELM) generally performed the best (49 and 57 out of 100 repetitions for reflectance and first derivative spectra, respectively) for estimating the chlorophyll content when assessed using the ratio of performance to deviation (RPD) values. Although SVM's robustness has been reported in some studies [59][60][61], and it performed best in 20 and 37 of the repeats, it also showed the worst performance in 28 and 33 repetitions for the reflectance and first derivative spectra, respectively. These results strongly suggest that SVM is not a stable method.…”

Predicting Wheat Yield at the Field Scale by Combining High-Resolution Sentinel-2 Satellite Imagery and Crop Modelling

“…Currently S2 can provide imagery every five days under ideal circumstances, which facilitates characterizing the entire crop life cycle at high temporal resolution. Some studies have utilized and validated the potential for using S2 for land cover classification [30], crop mapping [31,32], canopy chlorophyll and nitrogen content quantification [33,34] and yield estimation of other crops, with reasonable success [35][36][37][38].…”

Machine learning for high-throughput field phenotyping and image processing provides insight into the association of above and below-ground traits in cassava (Manihot esculenta Crantz)

“…Early detection and crop management associated with yield limitations can help increase productivity [4,23,80]. Crop yield prediction models could aid in early decision-making, optimizing the time required for eld evaluation, thus reducing the resources allocated to the research programs [81]. Furthermore, the predicted yield maps could also be used to implement variable rate technology (VRT) systems in spatial databases, thereby accomplishing precise eld-level inputs through the entire eld [82].…”

“…Remote sensing approaches can provide growers with nal yield assessments and show variations across the eld [79]. In remote sensing, MS imagery can describe crop development for potato tuber yield forecasting, across time and space, in a cost-effective manner [81,82].…”