Nondestructive estimation of potato yield using relative variables derived from multi-period LAI and hyperspectral data based on weighted growth stage

Methodological evolution of potato yield prediction: a comprehensive review

Timely and accurate prediction of crop yield is essential for increasing crop production, estimating planting insurance, and improving trade benefits. Potato (Solanum tuberosum L.) is a staple food in many parts of the world and improving its yield is necessary to ensure food security and promote related industries. We conducted a comprehensive literature survey to demonstrate methodological evolution of predicting potato yield. Publications on predicting potato yield based on methods of remote sensing (RS), crop growth model (CGM), and yield limiting factor (LF) were reviewed. RS, especially satellite-based RS, is crucial in potato yield prediction and decision support over large farm areas. In contrast, CGM are often utilized to optimize management measures and address climate change. Currently, combined with the advantages of low cost and easy operation, unmanned aerial vehicle (UAV) RS combined with artificial intelligence (AI) show superior potential for predicting potato yield in precision management of large-scale farms. However, studies on potato yield prediction are still limited in the number of varieties and field sample size. In the future, it is critical to employ time-series data from multiple sources for a wider range of varieties and large field sample sizes. This study aims to provide a comprehensive review of the progress in potato yield prediction studies and to provide a theoretical reference for related research on potato.

Cultivar-dependent differences in tuber growth cause increased soil resistance in potato fields

Since soil compaction of potato fields delays shoot emergence and decreases total yield, the causes and effects of this compaction need to be better understood. In a controlled environment trial with young (before tuber initiation) plants, roots of cv. Inca Bella (a phureja group cultivar) were more sensitive to increased soil resistance (3.0 MPa) than cv. Maris Piper (a tuberosum group cultivar). Such variation was hypothesized to cause yield differences in two field trials, in which compaction treatments were applied after tuber planting. Trial 1 increased initial soil resistance from 0.15 MPa to 0.3 MPa. By the end of the growing season, soil resistance increased three-fold in the upper 20 cm of the soil, but resistance in Maris Piper plots was up to twice that of Inca Bella plots. Maris Piper yield was 60% higher than Inca Bella and independent of soil compaction treatment, whilst compacted soil reduced Inca Bella yield by 30%. Trial 2 increased initial soil resistance from 0.2 MPa to 1.0 MPa. Soil resistance in the compacted treatments increased to similar, cultivar-dependent resistances as trial 1. Maris Piper yield was 12% higher than Inca Bella, but cultivar variation in yield response to compacted soil did not occur. Soil water content, root growth and tuber growth were measured to determine whether these factors could explain cultivar differences in soil resistance. Soil water content was similar between cultivars, thus did not cause soil resistance to vary between cultivars. Root density was insufficient to cause observed increases soil resistance. Finally, differences in soil resistance between cultivars became significant during tuber initiation, and became more pronounced until harvest. Increased tuber biomass volume (yield) of Maris Piper increased estimated mean soil density (and thus soil resistance) more than Inca Bella. This increase seems to depend on initial compaction, as soil resistance did not significantly increase in uncompacted soil. While increased soil resistance caused cultivar-dependent restriction of root density of young plants that was consistent with cultivar variation in yield, tuber growth likely caused cultivar-dependent increases in soil resistance in field trials, which may have further limited Inca Bella yield.

Multispectral remote sensing for accurate acquisition of rice phenotypes: Impacts of radiometric calibration and unmanned aerial vehicle flying altitudes

As a promising method, unmanned aerial vehicle (UAV) multispectral remote sensing (RS) has been extensively studied in precision agriculture. However, there are numerous problems to be solved in the data acquisition and processing, which limit its application. In this study, the Micro-MCA12 camera was used to obtain images at different altitudes. The piecewise empirical line (PEL) method suitable for predicting the reflectance of different ground objects was proposed to accurately acquire the reflectance of multi-altitude images by comparing the performance of the conventional methods. Several commonly utilized vegetation indices (VIs) were computed to estimate the rice growth parameters and yield. Then the rice growth monitoring and yield prediction were implemented to verify and evaluate the effects of radiometric calibration methods (RCMs) and UAV flying altitudes (UAV-FAs). The results show that the variation trends of reflectance and VIs are significantly different due to the change in component proportion observed at different altitudes. Except for the milking stage, the reflectance and VIs in other periods fluctuated greatly in the first 100 m and remained stable thereafter. This phenomenon was determined by the field of view of the sensor and the characteristic of the ground object. The selection of an appropriate calibration method was essential as a result of the marked differences in the rice phenotypes estimation accuracy based on different RCMs. There were pronounced differences in the accuracy of rice growth monitoring and yield estimation based on the 50 and 100 m-based variables, and the altitudes above 100 m had no notable effect on the results. This study can provide a reference for the application of UAV RS technology in precision agriculture and the accurate acquisition of crop phenotypes.

Multi-dimensional variables and feature parameter selection for aboveground biomass estimation of potato based on UAV multispectral imagery

Aboveground biomass (AGB) is an essential assessment of plant development and guiding agricultural production management in the field. Therefore, efficient and accurate access to crop AGB information can provide a timely and precise yield estimation, which is strong evidence for securing food supply and trade. In this study, the spectral, texture, geometric, and frequency-domain variables were extracted through multispectral imagery of drones, and each variable importance for different dimensional parameter combinations was computed by three feature parameter selection methods. The selected variables from the different combinations were used to perform potato AGB estimation. The results showed that compared with no feature parameter selection, the accuracy and robustness of the AGB prediction models were significantly improved after parameter selection. The random forest based on out-of-bag (RF-OOB) method was proved to be the most effective feature selection method, and in combination with RF regression, the coefficient of determination (R²) of the AGB validation model could reach 0.90, with root mean square error (RMSE), mean absolute error (MAE), and normalized RMSE (nRMSE) of 71.68 g/m², 51.27 g/m², and 11.56%, respectively. Meanwhile, the regression models of the RF-OOB method provided a good solution to the problem that high AGB values were underestimated with the variables of four dimensions. Moreover, the precision of AGB estimates was improved as the dimensionality of parameters increased. This present work can contribute to a rapid, efficient, and non-destructive means of obtaining AGB information for crops as well as provide technical support for high-throughput plant phenotypes screening.

A review of remote sensing for potato traits characterization in precision agriculture

Potato is one of the most significant food crops globally due to its essential role in the human diet. The growing demand for potato, coupled with severe environmental losses caused by extensive farming activities, implies the need for better crop protection and management practices. Precision agriculture is being well recognized as the solution as it deals with the management of spatial and temporal variability to improve agricultural returns and reduce environmental impact. As the initial step in precision agriculture, the traditional methods of crop and field characterization require a large input in labor, time, and cost. Recent developments in remote sensing technologies have facilitated the process of monitoring crops and quantifying field variations. Successful applications have been witnessed in the area of precision potato farming. Thus, this review reports the current knowledge on the applications of remote sensing technologies in precision potato trait characterization. We reviewed the commonly used imaging sensors and remote sensing platforms with the comparisons of their strengths and limitations and summarized the main applications of the remote sensing technologies in potato. As a result, this review could update potato agronomists and farmers with the latest approaches and research outcomes, as well as provide a selective list for those who have the intentions to apply remote sensing technologies to characterize potato traits for precision agriculture.

Prediction of the Nitrogen, Phosphorus and Potassium Contents in Grape Leaves at Different Growth Stages Based on UAV Multispectral Remote Sensing

The rapid and accurate acquisition of nitrogen, phosphorus and potassium nutrient contents in grape leaves is critical for improving grape yields and quality and for industrial development. In this study, crop growth was non-destructively monitored based on unmanned aerial vehicle (UAV) remote sensing technology. Three irrigation levels (W1, W2 and W3) and four fertilization levels (F3, F2, F1 and F0) were set in this study, and drip irrigation fertilization treatments adopted a complete block design. A correlation analysis was conducted using UAV multispectral image data obtained from 2019 to 2021 and the field-measured leaf nitrogen content (LNC), leaf potassium content (LKC) and leaf phosphorus content (LPC) values; from the results, the vegetation indices (VIs) that were sensitive to LNC, LKC and LPC were determined. By combining spectral indices with partial least squares (PLS), random forest (RF), support vector machine (SVM) and extreme learning machine (ELM) machine-learning algorithms, prediction models were established. Finally, the optimal combinations of spectral variables and machine learning models for predicting LNC, LPC and LKC in each grape growth period were determined. The results showed that: (1) there were high demands for nitrogen during the new shoot growth and flowering periods, potassium was the main nutrient absorbed in the fruit expansion period, and phosphorus was the main nutrient absorbed in the veraison and maturity periods; (2) combining multiple spectral variables with the RF, SVM and ELM models could result in improved LNC, LPC and LKC predictions. The optimal prediction model determination coefficient (R2) derived during the new shoot growth period was above 0.65, and that obtained during the other growth periods was above 0.75. The relative root mean square error (RRMSE) of the above models was below 0.20, and the Willmott consistency index (WIA) was above 0.88. In conclusion, UAV multispectral images have good application effects when predicting nutrient contents in grape leaves. This study can provide technical support for accurate vineyard nutrient management using UAV platforms.

Winter Wheat Yield Estimation Based on Optimal Weighted Vegetation Index and BHT-ARIMA Model

This study aims to use remote sensing (RS) time-series data to explore the intrinsic relationship between crop growth and yield formation at different fertility stages and construct a high-precision winter wheat yield estimation model applicable to short time-series RS data. Sentinel-2 images were acquired in this study at six key phenological stages (rejuvenation stage, rising stage, jointing stage, heading stage, filling stage, filling-maturity stage) of winter wheat growth, and various vegetation indexes (VIs) at different fertility stages were calculated. Based on the characteristics of yield data continuity, the RReliefF algorithm was introduced to filter the optimal vegetation index combinations suitable for the yield estimation of winter wheat for all fertility stages. The Absolutely Objective Improved Analytic Hierarchy Process (AOIAHP) was innovatively proposed to determine the proportional contribution of crop growth to yield formation in six different phenological stages. The selected VIs consisting of MTCI(RE2), EVI, REP, MTCI(RE1), RECI(RE1), NDVI(RE1), NDVI(RE3), NDVI(RE2), NDVI, and MSAVI were then fused with the weights of different fertility periods to obtain time-series weighted data. For the characteristics of short time length and a small number of sequences of RS time-series data in yield estimation, this study applied the multiplexed delayed embedding transformation (MDT) technique to realize the data augmentation of the original short time series. Tucker decomposition was performed on the block Hankel tensor (BHT) obtained after MDT enhancement, and the core tensor was extracted while preserving the intrinsic connection of the time-series data. Finally, the resulting multidimensional core tensor was trained with the Autoregressive Integrated Moving Average (ARIMA) model to obtain the BHT-ARIMA model for wheat yield estimation. Compared to the performance of the BHT-ARIMA model with unweighted time-series data as input, the weighted time-series input significantly improves yield estimation accuracy. The coefficients of determination (R2) were improved from 0.325 to 0.583. The root mean square error (RMSE) decreased from 492.990 to 323.637 kg/ha, the mean absolute error (MAE) dropped from 350.625 to 255.954, and the mean absolute percentage error (MAPE) decreased from 4.332% to 3.186%. Besides, BHT-ARMA and BHT-CNN models were also used to compare with BHT-ARIMA. The results indicated that the BHT-ARIMA model still had the best yield prediction accuracy. The proposed method of this study will provide fast and accurate guidance for crop yield estimation and will be of great value for the processing and application of time-series RS data.

Estimation of Above-Ground Biomass of Winter Wheat Based on Consumer-Grade Multi-Spectral UAV

One of the problems of optical remote sensing of crop above-ground biomass (AGB) is that vegetation indices (VIs) often saturate from the middle to late growth stages. This study focuses on combining VIs acquired by a consumer-grade multiple-spectral UAV and machine learning regression techniques to (i) determine the optimal time window for AGB estimation of winter wheat and to (ii) determine the optimal combination of multi-spectral VIs and regression algorithms. UAV-based multi-spectral data and manually measured AGB of winter wheat, under five nitrogen rates, were obtained from the jointing stage until 25 days after flowering in the growing season 2020/2021. Forty-four multi-spectral VIs were used in the linear regression (LR), partial least squares regression (PLSR), and random forest (RF) models in this study. Results of LR models showed that the heading stage was the most suitable stage for AGB prediction, with R2 values varying from 0.48 to 0.93. Three PLSR models based on different datasets performed differently in estimating AGB in the training dataset (R2 = 0.74~0.92, RMSE = 0.95~2.87 t/ha, MAE = 0.75~2.18 t/ha, and RPD = 2.00~3.67) and validation dataset (R2 = 0.50~0.75, RMSE = 1.56~2.57 t/ha, MAE = 1.44~2.05 t/ha, RPD = 1.45~1.89). Compared with PLSR models, the performance of the RF models was more stable in the prediction of AGB in the training dataset (R2 = 0.95~0.97, RMSE = 0.58~1.08 t/ha, MAE = 0.46~0.89 t/ha, and RPD = 3.95~6.35) and validation dataset (R2 = 0.83~0.93, RMSE = 0.93~2.34 t/ha, MAE = 0.72~2.01 t/ha, RPD = 1.36~3.79). Monitoring AGB prior to flowering was found to be more effective than post-flowering. Moreover, this study demonstrates that it is feasible to estimate AGB for multiple growth stages of winter wheat by combining the optimal VIs and PLSR and RF models, which overcomes the saturation problem of using individual VI-based linear regression models.

Remotely sensed estimation of total iron content in soil with harmonic analysis and BP neural network

BACKGROUND

The estimation of total iron content at the regional scale is of much significance as iron deficiency has become a routine problem for many crops.

METHODS

In this study, a novel method for estimating total iron content in soil (TICS) was proposed using harmonic analysis (HA) and back propagation (BP) neural network model. Several data preprocessing methods of first derivative (FD), wavelet packet transform (WPT), and HA were conducted to improve the correlation between the soil spectra and TICS. The principal component analysis (PCA) was exploited to obtained three kinds of characteristic variables (FD, WPT-FD, and WPT-FD-HA) for TICS estimation. Furthermore, the estimated accuracy of three BP models based on these variables was compared.

RESULTS

The results showed that the BP models of different soil types based on WPT-FD-HA had better estimation accuracy, with the highest R² value of 0.95, and the RMSE of 0.68 for the loessial soil. It was proved that the characteristic variable obtained by harmonic decomposition improved the validity of the input variables and the estimation accuracy of the TICS models. Meanwhile, it was identified that the WPT-FD-HA-BP model can not only estimate the total iron content of a single soil type with high accuracy but also demonstrate a good effect on the estimation of TICS of mixed soil.

CONCLUSION

The HA method and BP neural network combined with WPT and FD have great potential in TICS estimation under the conditions of single soil and mixed soil. This method can be expected to be applied to the prediction of crop biochemical parameters.

Impacts of climate change on suitability zonation for potato cultivation in Jilin Province, Northeast China

Global climate change is causing notable shifts in the environmental suitability of the main regions involved in potato cultivation and has, thus, changed the production potential of potatoes. These shifts can be mapped at fine scales to better understand climate change within areas of potato cultivation and to find infrastructural- and breeding-based solutions. As a case study, we have identified and mapped the structural and spatial shifts that occurred in areas suitable for potato cultivation in Jilin Province, China. We identified a discontinuity in climate change trends between 1961 and 2018 based on data for Jilin Province, and analyzed the averages and linear trends for six important climatic parameters. We used the averages of these climatic parameters to establish climate models for the province and determined cultivation using a multi-criteria, decision-based model that integrates Analytical Hierarchy Process Weighted Principal Component Analysis (AHP-PCA) and Geographic Information System (GIS). We mapped the environmentally suitable areas for potato cultivation at a 3-km resolution based on the geo-climate model for each time period and analyzed differences between them. We found that "Most suitable” areas for potato cultivation were mainly distributed in the central area of Jilin Province, “Suitable” areas were located in the northwestern plains, and “Sub-suitable” areas were located in the eastern mountainous areas. In contrast, “Not suitable” areas occur mainly in the high-altitude areas in the east. The areas of “Most suitable” and “Suitable” areas for potato cultivation in Jilin Province were increasing, with increasing rates of 0.37 × 1,000 km² decade⁻¹ (R² = 0.58, P < 0.01) and 0.20 × 1,000 km² decade⁻¹ (R² = 0.28, P < 0.01), respectively, while the extent of “Sub-suitable” areas is decreasing, with a decreasing rate of 0.58 × 1,000 km² decade⁻¹ (R² = 0.53, P < 0.05). The area of “Not suitable” areas had undergone little change. “Most suitable” and “Suitable” areas for potato cultivation showed a trend towards northward expansion. Overall, our results suggest that global climate change has had a positive impact on potato cultivation in Jilin Province over the past 58 years.

Improving Potato Yield Prediction by Combining Cultivar Information and UAV Remote Sensing Data Using Machine Learning

Accurate high-resolution yield maps are essential for identifying spatial yield variability patterns, determining key factors influencing yield variability, and providing site-specific management insights in precision agriculture. Cultivar differences can significantly influence potato (Solanum tuberosum L.) tuber yield prediction using remote sensing technologies. The objective of this study was to improve potato yield prediction using unmanned aerial vehicle (UAV) remote sensing by incorporating cultivar information with machine learning methods. Small plot experiments involving different cultivars and nitrogen (N) rates were conducted in 2018 and 2019. UAV-based multi-spectral images were collected throughout the growing season. Machine learning models, i.e., random forest regression (RFR) and support vector regression (SVR), were used to combine different vegetation indices with cultivar information. It was found that UAV-based spectral data from the early growing season at the tuber initiation stage (late June) were more correlated with potato marketable yield than the spectral data from the later growing season at the tuber maturation stage. However, the best performing vegetation indices and the best timing for potato yield prediction varied with cultivars. The performance of the RFR and SVR models using only remote sensing data was unsatisfactory (R2 = 0.48–0.51 for validation) but was significantly improved when cultivar information was incorporated (R2 = 0.75–0.79 for validation). It is concluded that combining high spatial-resolution UAV images and cultivar information using machine learning algorithms can significantly improve potato yield prediction than methods without using cultivar information. More studies are needed to improve potato yield prediction using more detailed cultivar information, soil and landscape variables, and management information, as well as more advanced machine learning models.

An Efficient Method for Estimating Wheat Heading Dates Using UAV Images

Convenient, efficient, and high-throughput estimation of wheat heading dates is of great significance in plant sciences and agricultural research. However, documenting heading dates is time-consuming, labor-intensive, and subjective on a large-scale field. To overcome these challenges, model- and image-based approaches are used to estimate heading dates. Phenology models usually require complicated parameters calibrations, making it difficult to model other varieties and different locations, while in situ field-image recognition usually requires the deployment of a large amount of observational equipment, which is expensive. Therefore, in this study, we proposed a growth curve-based method for estimating wheat heading dates. The method first generates a height-based continuous growth curve based on five time-series unmanned aerial vehicle (UAV) images captured over the entire wheat growth cycle (>200 d). Then estimate the heading date by generated growth curve. As a result, the proposed method had a mean absolute error of 2.81 d and a root mean square error of 3.49 d for 72 wheat plots composed of different varieties and densities sown on different dates. Thus, the proposed method is straightforward, efficient, and affordable and meets the high-throughput estimation requirements of large-scale fields and underdeveloped areas.

Estimating Above-Ground Biomass of Potato Using Random Forest and Optimized Hyperspectral Indices

Spectral indices rarely show consistency in estimating crop traits across growth stages; thus, it is critical to simultaneously evaluate a group of spectral variables and select the most informative spectral indices for retrieving crop traits. The objective of this study was to explore the optimal spectral predictors for above-ground biomass (AGB) by applying Random Forest (RF) on three types of spectral predictors: the full spectrum, published spectral indices (Pub-SIs), and optimized spectral indices (Opt-SIs). Canopy hyperspectral reflectance of potato plants, treated with seven nitrogen (N) rates, was obtained during the tuber formation and tuber bulking from 2015 to 2016. Twelve Pub-SIs were selected, and their spectral bands were optimized using band optimization algorithms. Results showed that the Opt-SIs were the best input variables of RF models. Compared to the best empirical model based on Opt-SIs, the Opt-SIs based RF model improved the prediction of AGB, with R2 increased by 6%, 10%, and 16% at the tuber formation, tuber bulking, and for across the two growth stages, respectively. The Opt-SIs can significantly reduce the number of input variables. The optimized Blue nitrogen index (Opt-BNI) and Modified red-edge normalized difference vegetation index (Opt-mND705) combined with an RF model showed the best performance in estimating potato AGB at the tuber formation stage (R2 = 0.88). In the tuber bulking stage, only using optimized Nitrogen planar domain index (Opt-NPDI) as the input variable of the RF model produced satisfactory accuracy in training and testing datasets, with the R2, RMSE, and RE being 0.92, 208.6 kg/ha, and 10.3%, respectively. The Opt-BNI and Double-peak nitrogen index (Opt-NDDA) coupling with an RF model explained 86% of the variations in potato AGB, with the lowest RMSE (262.9 kg/ha) and RE (14.8%) across two growth stages. This study shows that combining the Opt-SIs and RF can greatly enhance the prediction accuracy for crop AGB while significantly reduces collinearity and redundancies of spectral data.

Comparison of Crop Trait Retrieval Strategies Using UAV-Based VNIR Hyperspectral Imaging

Hyperspectral cameras onboard unmanned aerial vehicles (UAVs) have recently emerged for monitoring crop traits at the sub-field scale. Different physical, statistical, and hybrid methods for crop trait retrieval have been developed. However, spectra collected from UAVs can be confounded by various issues, including illumination variation throughout the crop growing season, the effect of which on the retrieval performance is not well understood at present. In this study, four retrieval methods are compared, in terms of retrieving the leaf area index (LAI), fractional vegetation cover (fCover), and canopy chlorophyll content (CCC) of potato plants over an agricultural field for six dates during the growing season. We analyzed: (1) The standard look-up table method (LUTstd), (2) an improved (regularized) LUT method that involves variable correlation (LUTreg), (3) hybrid methods, and (4) random forest regression without (RF) and with (RFexp) the exposure time as an additional explanatory variable. The Soil-Leaf-Canopy (SLC) model was used in association with the LUT-based inversion and hybrid methods, while the statistical modelling methods (RF and RFexp) relied entirely on in situ data. The results revealed that RFexp was the best-performing method, yielding the highest accuracies, in terms of the normalized root mean square error (NRMSE), for LAI (5.36%), fCover (5.87%), and CCC (15.01%). RFexp was able to reduce the effects of illumination variability and cloud shadows. LUTreg outperformed the other two retrieval methods (hybrid methods and LUTstd), with an NRMSE of 9.18% for LAI, 10.46% for fCover, and 12.16% for CCC. Conversely, LUTreg led to lower accuracies than those derived from RF for LAI (5.51%) and for fCover (6.23%), but not for CCC (16.21%). Therefore, the machine learning approaches-in particular, RF-appear to be the most promising retrieval methods for application to UAV-based hyperspectral data.