Smart Horticulture: Latest Advances and Prospects

The objective of this research was to assess the feasibility of remote sensing (RS) technology, specifically an unmanned aerial system (UAS), to estimate Bambara groundnut canopy state variables including leaf area index (LAI), canopy chlorophyll content (CCC), aboveground biomass (AGB), and fractional vegetation cover (FVC). RS and ground data were acquired during Malaysia’s 2018/2019 Bambara groundnut growing season at six phenological stages; vegetative, flowering, podding, podfilling, maturity, and senescence. Five vegetation indices (VIs) were determined from the RS data, resulting in single-stage VIs and cumulative VIs (∑VIs). Pearson’s correlation was used to investigate the relationship between canopy state variables and single stage VIs and ∑VIs over several stages. Linear parametric and non-linear non-parametric machine learning (ML) regressions including CatBoost Regressor (CBR), Random Forest Regressor (RFR), AdaBoost Regressor (ABR), Huber Regressor (HR), Multiple Linear Regressor (MLR), Theil-Sen Regressor (TSR), Partial Least Squares Regressor (PLSR), and Ridge Regressor (RR) were used to estimate canopy state variables using VIs/∑VIs as input. The best single-stage correlations between canopy state variables and VIs were observed at flowering (r > 0.50 in most cases). Moreover, ∑VIs acquired from vegetative to senescence stage had the strongest correlation with all measured canopy state variables (r > 0.70 in most cases). In estimating AGB, MLR achieved the best testing performance (R² = 0.77, RMSE = 0.30). For CCC, RFR excelled with R² of 0.85 and RMSE of 2.88. Most models performed well in FVC estimation with testing R² of 0.98–0.99 and low RMSE. For LAI, MLR stood out in testing with R² of 0.74, and RMSE of 0.63. Results demonstrate the UAS-based RS technology potential for estimating Bambara groundnut canopy variables. Full article

Accurate and rapid determination of moisture content is essential in crop production and decision-making for irrigation. Near-infrared (NIR) spectroscopy has been shown to be a promising method for determining moisture content in various agricultural products, including herbs and vegetables. This study tested the hypothesis that NIR spectroscopy is effective in accurately measuring the moisture content of Genovese basil (Ocimum basilicum L.), with the objective of developing a respective calibration model. Spectral data were obtained from a total of 120 basil leaf samples over a period of six days. These included freshly harvested and detached leaves, as well as those left in ambient air for 1–6 days. Five spectra were taken from each leaf using a handheld NIR spectrophotometer, which covers the first and second overtones of the NIR spectral region: 950–1650 nm. After the spectral acquisition, the leaves were weighed for fresh mass and then put in an oven for 72 h at 80 °C to determine the dry weight and calculate the reference moisture content. The calibration model was developed using multivariate analysis in MATLAB, including preprocessing and regression modeling. The data obtained from 75% of the samples were used for model training and 25% for validation. The final model demonstrates strong performance metrics. The root mean square error of calibration (RMSEC) is 2.9908, the root mean square error of cross-validation (RMSECV) is 3.2368, and the root mean square error of prediction (RMSEP) reaches 2.4675. The coefficients of determination for calibration (R²C) and cross-validation (R²CV) are consistent, with values of 0.829 and 0.80, respectively. The model’s predictive ability is indicated by a coefficient of determination for prediction (R²P) of 0.86. The range error ratio (RER) stands at 11.045—highlighting its predictive performance. Our investigation, using handheld NIR spectrophotometry, confirms NIR’s usefulness in basil moisture determination. The rapid determination offers valuable insights for irrigation and crop management. Full article

The quality of radish roots depends largely on its cultivar, production environment, and postharvest management along the supply chain. Quality monitoring of fresh products is of utmost importance during the postharvest period. The purpose of this study is to nondestructively estimate the weight of a radish using random forests based on color and shape information obtained from images, as well as volumetric information obtained by analyzing a point cloud obtained by combining multiple forms of shape information. The explanatory variables were color and shape information obtained through an image analysis of still images of radishes captured in a constructed photographic environment. The volume information was calculated from the bounding box and convex hull applied to the point cloud by combining the shape information obtained from the image analysis. We then applied random forests to relate the radish weight to the explanatory variables. The experimental results showed that the models using color, shape, or volume information all exhibited good performance with a Pearson’s correlation coefficient (COR) ≥ 0.80, suggesting the potential of nondestructive monitoring of radish weight based on color, shape, and volume information. Specifically, the model using volume information showed very high performance, with a COR of 0.95 or higher. Full article

A patent portfolio focusing on sensors for the measurement of fruit properties was generated and analyzed with the aim of contributing to a better understanding of the trends in the development and application of sensors intended for measuring fruit properties and their changes. A patent portfolio of 189 patents, utility models and patent applications was formed. Three groups of patents were identified: (i) sensor-based measurement of individual parameters, (ii) multisensor solutions for the simultaneous monitoring of multiple relevant aspects and (iii) solutions integrating sensor-derived data with artificial intelligence tools and techniques. The analysis of the patent portfolio pointed out the main driving forces of technology strengthening in the field of fruit property measurement. The development of sensing technologies enables the real-time, rapid and cost-effective determination of ever-increasing and more sophisticated sets of fruit properties and environmental conditions. Solutions integrating different sensing technologies into multisensor systems for monitoring fruit quality, ripening or freshness as holistic concepts opens avenues for the introduction of a new approach to fresh produce management. Increasing numbers of solutions introducing the application of artificial intelligence tools such as computer vision, machine learning and deep learning into the fresh produce supply chain contribute to the possibilities of substituting human decision-making at points of relevance for fresh produce management with optimal evidence-based solutions. Full article

This study presents an innovative approach to fruit measurement using 3D imaging, focusing on Japanese quince (Chaenomeles japonica) cultivated in Latvia. The research consisted of two phases: manual measurements of fruit parameters (length and width) using a calliper and 3D imaging using an algorithm based on k-nearest neighbors (k-NN), the ingeniously designed “Imaginary Square” method, and object projection analysis. Our results revealed discrepancies between manual measurements and 3D imaging data, highlighting challenges in the precision and accuracy of 3D imaging techniques. The study identified two primary constraints: variability in fruit positioning on the scanning platform and difficulties in distinguishing individual fruits in close proximity. These limitations underscore the need for improved algorithmic capabilities to handle diverse spatial orientations and proximities. Our findings emphasize the importance of refining 3D scanning techniques for better reliability and accuracy in agricultural applications. Enhancements in image processing, depth perception algorithms, and machine learning models are crucial for effective implementation in diverse agricultural scenarios. This research not only contributes to the scientific understanding of 3D imaging in horticulture but also underscores its potential and limitations in advancing sustainable and productive farming practices. Full article

Early detection of drought stress in greenhouse tomato (Solanum lycopersicum) is an important issue. Real-time and nondestructive assessment of plant water status is possible by spectroscopy. However, spectral data often suffer from the problems of collinearity, class imbalance, and class overlap, which require some effective strategies to overcome. This study used a spectroscopic dataset on the tomato (cv. ‘Rosada’) vegetative stage and calculated ten spectral reflectance indices (SRIs) to develop an early drought detection model for greenhouse tomatoes. In addition, this study applied the random forest (RF) algorithm and two resampling techniques to explore efficient methods for analyzing multiple SRI data. It was found that the use of the RF algorithm to build a prediction model could overcome collinearity. Moreover, the synthetic minority oversampling technique could improve the model performance when the data were imbalanced. For class overlap in high-dimensional data, this study suggested that two to three important predictors can be screened out, and it then used a scatter plot to decide whether the class overlap should be addressed. Finally, this study proposed an RF model for detecting early drought stress based on three SRIs, namely, RNDVI, SPRI, and SR2, which only needs six spectral wavebands (i.e., 510, 560, 680, 705, 750, and 900 nm) to achieve more than 85% accuracy. This model can be a useful and cost-effective tool for precise irrigation in greenhouse tomato production, and its sensor prototype can be developed and tested in different situations in the future. Full article

Leaf Soil-Plant Analysis Development (SPAD) prediction is a crucial measure of plant health and is essential for optimizing indoor plant management. The deep learning methods offer advanced tools for precise evaluations but their adaptation to the heterogeneous indoor plant ecosystem presents distinct challenges. This study assesses how accurately deep neural network (DNN) predicts SPAD values in leaves on indoor plants when compared to well-established machine learning techniques, including Random Forest (RF) and Extreme Gradient Boosting (XGB). The covariates for prediction were based on low-cost multispectral and soil electro-conductivity (EC) sensors, enabling a non-destructive sensing approach. The study also strongly emphasized multicollinearity analysis quantified by the Variance Inflation Factor (VIF) and two independent indices, as well as its effect on prediction accuracy using deep and machine learning methods. DNN resulted in higher accuracy to RF and XGB, also performing better using filtered data after multicollinearity analysis based on the coefficient of determination (R²), root mean square error (RMSE) and mean absolute error (MAE) (R² = 0.589, RMSE = 11.68, MAE = 9.52) in comparison to using all input covariates (R² = 0.476, RMSE = 12.90, MAE = 10.94). Overall, DNN was proven as a more accurate prediction method than the conventional machine learning approach for the prediction of leaf SPAD values in indoor plants, despite using heterogenous plant types and input covariates. Full article

The primary objective of this research was to ascertain the optimal circumstances for the successful growth of black chokeberry (Aronia melanocarpa (Michx.) Elliott) using tissue culture techniques. Additionally, the study aimed to explore the potential use of machine learning algorithms in this context. The present research investigated a range of in vitro parameters such as total number of roots (TNR), longest root length (LRL), average root length (ARL), number of main roots (NMR), number of siblings (NS), shoot length (SL), shoot diameter (SD), leaf width (LW), and leaf length (LL) for Aronia explants cultivated in different media (Murashige and Skoog (MS) and woody plant medium (WPM)) with different concentrations (0, 0.5, 1, 1.5, and 2 mg L⁻¹) of indole-3-butyric acid (IBA). The study showed that IBA hormone levels may affect WPM properties, affecting the LRL and ARL variables. Aronia explant media treated with 2 mg L⁻¹ IBA had the greatest TNR, NMR, NS, SL, and SD values; 31.67 pieces, 2.37 pieces, 5.25 pieces, 66.60 mm, and 2.59 mm, in that order. However, Aronia explants treated with 1 mg L⁻¹ IBA had the highest LW (9.10 mm) and LL (14.58 mm) values. Finally, Aronia explants containing 0.5 mg L⁻¹ IBA had the greatest LRL (89.10 mm) and ARL (57.57 mm) values. In general, the results observed (TNR, LRL, ARL, NMR, NS, SL, SD, LW, and LL) indicate that Aronia explants exhibit superior growth and development in WPM (25.68 pieces, 68.10 mm, 51.64 mm, 2.17 pieces, 4.33 pieces, 57.95 mm, 2.49 mm, 8.08 mm, and 14.26 mm, respectively) as opposed to MS medium (20.27 pieces, 59.92 mm, 47.25 mm, 1.83 pieces, 3.57 pieces, 49.34 mm, 2.13 mm, 6.99 mm, and 12.21 mm, respectively). In the context of the in vitro culturing of Aronia explants utilizing MS medium and WPM, an analysis of machine learning models revealed that the XGBoost and SVM models perform better than the RF, KNN, and GP models when it comes to making predictions about those variables. In particular, the XGBoost model stood out due to the fact that it had the greatest R-squared value, and showed higher predictive ability in terms of properly forecasting values in comparison to actual outcomes. The findings of a linear regression (LR) analysis were used in order to conduct an efficacy study of the XGBoost model. The LR results especially confirmed the findings for the SD, NS, and NMR variables, whose R-squared values were more than 0.7. This demonstrates the extraordinary accuracy that XGboost has in predicting these particular variables. As a consequence of this, it is anticipated that it will be beneficial to make use of the XGboost model in the dosage optimization and estimation of in vitro parameters in micropropagation studies of the Aronia plant for further scientific investigation. Full article

Nutrient monitoring in Micro Indoor Smart Hydroponics (MISH) relies on measuring electrical conductivity or total dissolved solids to determine the amount of nutrients in a hydroponic solution. Neither method can distinguish concentrations of individual nutrients. This study presents the development and testing of a novel spectroscopic sensor system to monitor nitrogen changes in nutrient solutions for MISH systems. The design phase determined that using an inexpensive AS7265x Internet of Thing (IoT) sensor in a transflective spectroscopic application could effectively detect small fluctuations in nitrogen concentraation. Next, a novel transflective sensor apparatus was designed and constructed for use in a MISH system experiment, growing lettuce over 30 days. Two solution tanks of different sizes, 80 L and 40 L, were used in the deployment of the system. Samples from each tank were analyzed for nitrogen concentration in a laboratory, and multilinear regression was used to predict the nitrogen concentrations using the AS7265x 18 spectral channels recorded in the sensor system. Significant results were found for both tanks with an R² of 0.904 and 0.911 for the 80 and 40 L tanks, respectively. However, while the use of all wavelengths produced an accurate model, none of the individual wavelengths were indicative on their own. These findings indicate that the novel system presented in this study successfully and accurately monitors changes in nitrogen concentrations for MISH systems, using low cost IoT sensors. Full article

Moisture and potassium deficiency are two of the main limiting variables for squash crop performance in many water-stressed places worldwide. If major output decreases are to be avoided, it is critical to detect signs of crop stress as early as possible in the growth cycle. Proximal remote sensing can be a reliable technique for offering a rapid and precise instrument and localized management tool. This study tested the ability of proximal hyperspectral remotely sensed data to predict squash traits in two successive seasons (spring and fall) with varying moisture and potassium rates. Spectral data were collected from drip-irrigated squash that had been treated to varied rates of irrigation and potassium fertilization over both investigated seasons. To forecast potassium-use efficiency (KUE), chlorophyll meter (Chlm), water-use efficiency (WUE), and seed yield (SY) of squash, different commonly used and newly-introduced spectral index values for three bands (3D-SRIs), as well as a Decision Tree (DT) model, were evaluated. The results revealed that the newly constructed three-band SRIs based on the wavelengths of the visible (VIS), near-infrared (NIR), and red-edge regions were sensitive enough to measure the four tested parameters of squash in this study. For instance, NDI_558,646,708 presented the highest R² of 0.75 for KUE, NDI_744,746,738 presented the highest R² of 0.65 for Chlm, and NDI_670,628,392 presented the highest R² of 0.64 for SY of squash. The results further demonstrated that the principal component analysis (PCA) demonstrated the ability to distinguish moisture stress from potassium deficiency stress at the flowering stage onwards. Combining 3D-SRIs, DT-based bands (DT-b), and the aggregate of all spectral characteristics (ASF) with DT models would be an effective strategy for estimating four observed parameters with appropriate accuracy. For example, the model’s approximately 30 spectral characteristics were extremely important for predicting KUE. Its outputs with R² were, for the training and validation datasets, 0.967 (RMSE = 0.175) and 0.818 (RMSE = 0.284), respectively. For measuring Chlm, the DT-DT-b-20 model demonstrated the best. In the training and validation datasets, the R² value was 0.993 (RMSE = 0.522) and 0.692 (RMSE = 2.321), respectively. The overall outcomes showed that proximal-reflectance-sensing-based 3D-SRIs and DT models based on 3D-SRIs, DT-b, and ASF could be used to evaluate the four tested parameters of squash under different levels of irrigation regimes and potassium fertilizer. Full article

Coffee producers are ever more interested in understanding the dynamics of coffee’s spatial and temporal variability. However, it is necessary to obtain high-density yield data for decision-making. The objective of this study is to evaluate the quality of yield data obtained through a yield monitor onboard a coffee harvester, as well as to evaluate the potential of the data collected over three harvests. The yield monitor validation data showed a high correlation (above R² 0.968) when compared with the data obtained by a wagon instrumented with load cells. It was also possible to obtain yield maps for three consecutive seasons, allowing the identification of their internal variability, as well as classifying regions that show alternating yield patterns between years as the expression of the biennial yield behavior manifested inside and along the field, in addition to the spatial variability. This result indicates that, in addition to knowing the spatial yield variability, the biennial variance information must also be considered in the strategies for site-specific management. Regions that presented high yield variance should be alternated according to the productive year (high and low yield) and not only in consideration of their yield variability as on the regions with more stable yield behavior over time. The use of yield data can help the producer make more assertive decisions for crop and farm management. Full article