Sensory guided selection criteria for breeding consumer-preferred sweetpotatos in Uganda

Machine learning methods in near infrared spectroscopy for predicting sensory traits in sweetpotatoes

It has been established that near infrared (NIR) spectroscopy has the potential of estimating sensory traits given the direct spectral responses that these properties have in the NIR region. In sweetpotato, sensory and texture traits are key for improving acceptability of the crop for food security and nutrition. Studies have statistically modelled the levels of NIR spectroscopy sensory characteristics using partial least squares (PLS) regression methods. To improve prediction accuracy, there are many advanced techniques, which could enhance modelling of fresh (wet and un-processed) samples or nonlinear dependence relationships. Performance of different quantitative prediction models for sensory traits developed using different machine learning methods were compared. Overall, results show that linear methods; linear support vector machine (L-SVM), principal component regression (PCR) and PLS exhibited higher mean R2 values than other statistical methods. For all the 27 sensory traits, calibration models using L-SVM and PCR has slightly higher overall R2 (x¯ = 0.33) compared to PLS (x¯ = 0.32) and radial-based SVM (NL-SVM; x¯= 0.30). The levels of orange color intensity were the best predicted by all the calibration models (R2 = 0.87 - 0.89). The elastic net linear regression (ENR) and tree-based methods; extreme gradient boost (XGBoost) and random forest (RF) performed worse than would be expected but could possibly be improved with increased sample size. Lower average R2 values were observed for calibration models of ENR (x¯ = 0.26), XGBoost (x¯ = 0.26) and RF (x¯ = 0.22). The overall RMSE in calibration models was lower in PCR models (X = 0.82) compared to L-SVM (x¯ = 0.86) and PLS (x¯ = 0.90). ENR, XGBoost and RF also had higher RMSE (x¯ = 0.90 - 0.92). Effective wavelengths selection using the interval partial least-squares regression (iPLS), improved the performance of the models but did not perform as good as the PLS. SNV pre-treatment was useful in improving model performance.

Combined use of sensory methods for the selection of root, tuber and banana varieties acceptable to end-users

BACKGROUND

The assessment of user acceptability in relation to crop quality traits should be a full part of breeding selection programs. Our methodology is based on a combination of sensory approaches aiming to evaluate the sensory characteristics and user acceptability of root, tuber and banana (RTB) varieties.

RESULTS

The four-stepped approach links sensory characteristics to physicochemical properties and end-user acceptance. It starts with the development of key quality traits using qualitative approaches (surveys and ranking) and it applies a range of sensory tests such as Quantitative Descriptive Analysis with a trained panel, Check-All-That-apply, nine-point hedonic scale and Just-About-Right with consumers. Results obtained on the same samples from the consumer acceptance, sensory testing and physicochemical testing are combined to explore correlations and develop acceptability thresholds.

CONCLUSION

A combined qualitative and quantitative approach involving different sensory techniques is necessary to capture sensory acceptance of products from new RTB clones. Some sensory traits can be correlated with physicochemical characteristics and could be evaluated using laboratory instruments (e.g. texture). Other traits (e.g. aroma and mealiness) are more difficult to predict, and the use of a sensory panel is still necessary. For these latter traits, more advanced physicochemical methods that could accelerate the breeding selection through high throughput phenotyping are still to be developed. © 2023 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Decision tree scoring system to guide selection for consumer preference in sweetpotato breeding trials

BACKGROUND

Previously, a lexicon and protocol for quantitative descriptive analysis (QDA) was established for the Uganda sweetpotato breeding program. The implication of QDA scores for priority sensory attributes on consumer preference should be determined to interpret results efficiently and make decisions effectively. The present study aimed to develop a gender-responsive decision tree to obtain an overall sweetpotato eating quality score to facilitate demand-led targeted breeding selection. It focused on Kamuli and Hoima districts (Uganda) and uses pre-lease advanced clones ('NKB3', 'NKB105', 'NKB135', 'D11' and 'D20'), released varieties ('NASPOT 8' and 'NAROSPOT 1') and landraces ('Muwulu-Aduduma', 'Umbrella').

RESULTS

Including boiled sweetpotato sensory characteristics, namely mealy, sweet taste, sweetpotato smell, firm and not fibrous, in breeding design would benefit end-users, especially women given their role in varietal selection, food preparation and marketing. 'D20', 'NASPOT 8' and 'NAROSPOT 1' were most liked in both districts. 'NKB3' and 'D11' were the least liked in Hoima, whereas 'Muwulu-Aduduma' was the least liked in Kamuli. There was a positive correlation between color and overall liking (r2 = 0.8) and consumers liked the color (average rating ≥ 6 on a nine-point hedonic scale) of all genotypes. Threshold values (average rating on 11-point scales) for consumer acceptability were identified (sweet taste = 6, sweetpotato aroma and flavor = 6, firmness = 3, and mealiness = 4). A regression decision tree tool was created to calculate an eating quality selection index when screening lines in breeding programs using the values.

CONCLUSION

Decision trees that include consumer needs and gender considerations would facilitate demand-led breeding and make varietal selection in sweetpotato breeding programs more effective. © 2023 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Baked sweetpotato textures and sweetness: An investigation into relationships between physicochemical and cooked attributes

Sweetpotato varieties vary greatly in perceived textures and sweetness. This study identified physicochemical factors that influence these attributes in cooked sweetpotatoes. Fifteen genotypes grown on three plots were baked and evaluated by a trained descriptive sensory analysis panel for sweetness and 13 texture attributes. Mechanical parameters were measured by texture profile analysis (TPA); and composition (starch, cell wall material, sugar contents), starch properties (thermal, granule type ratios, granule sizes), and amylase activities were characterized. TPA predicted fracturability and firmness well, whereas starch and sugar contents, B-type starch granule ratio, and amylase activities influenced prediction of mouthfeel textures. Sweetness perception was influenced by perceived particle size and sugar contents; and maltose generation during baking was highly correlated with raw sweetpotato starch content. These relationships between physicochemical sweetpotato properties and baked textures and sweetness could benefit breeders and processors in selecting biochemical traits that result in consumer preferred products.

A case of transdisciplinarity and collaborative decision making: the co-construction of Gendered Food Product Profiles

Crop breeding in sub-Saharan Africa has made considerable gains; however, postharvest and food-related preferences have been overlooked, in addition to how these preferences vary by gender, social difference and context. This context is changing as participatory approaches using intersectional gender and place-based methods are beginning to inform how breeding programmes make decisions. This article presents an innovative methodology to inclusively and democratically prioritise food quality traits of root, tuber and banana crops based on engagement with food systems actors and transdisciplinary collaboration. The outcome of the methodology is the Gendered Food Product Profile (GFPP) - a list of prioritised food quality characteristics - to support breeders to make more socially inclusive decisions on the methods for trait characterisation to select genotypes closer to the needs of food system actors. This article reviews application of the methodology in 14 GFPPs, presents illustrative case studies and lessons learned. Key lessons are that the transdisciplinary structure and the key role of social scientists helped avoid reductionism, supported co-learning, and the creation of GFPPs that represented the diverse interests of food system actors, particularly women, in situ. The method partially addressed power dynamics in multidisciplinary decision making; however, effectiveness was dependent on equitable team relations and supportive institutions committed to valuing plural forms of knowledge. Actions to address power asymmetries that privilege particular types of knowledge and voices in decision making are crucial in techno-science projects, along with opportunities for co-learning and long-term collaboration and a transdisciplinary structure at higher level. © 2024 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Potato and sweetpotato breeding at the international potato center: approaches, outcomes and the way forward

Root and tuber crop breeding is at the front and center of CIP's science program, which seeks to develop and disseminate sustainable agri-food technologies, information and practices to serve objectives including poverty alleviation, income generation, food security and the sustainable use of natural resources. CIP was established in 1971 in Peru, which is part of potato's center of origin and diversity, with an initial mandate on potato and expanding to include sweetpotato in 1986. Potato and sweetpotato are among the top 10 most consumed food staples globally and provide some of the most affordable sources of energy and vital nutrients. Sweetpotato plays a key role in securing food for many households in Africa and South Asia, while potato is important worldwide. Both crops grow in a range of conditions with relatively few inputs and simple agronomic techniques. Potato is adapted to the cooler environments, while sweetpotato grows well in hot climates, and hence, the two crops complement each other. Germplasm enhancement (pre-breeding), the development of new varieties and building capacity for breeding and variety testing in changing climates with emphasis on adaptation, resistance, nutritional quality and resource-use efficiency are CIP's central activities with significant benefits to the poor. Investments in potato and sweetpotato breeding and allied disciplines at CIP have resulted in the release of many varieties some of which have had documented impact in the release countries. Partnership with diverse types of organizations has been key to the centers way of working toward improving livelihoods through crop production in the global South.

Gender mainstreaming in sweetpotato breeding in Uganda: a case study

Purpose

In Uganda, sweetpotato [Ipomoea batatas (L.) Lam] is typically a "woman's crop," grown, processed, stored and also mainly consumed by smallholder farmers for food and income. Farmers value sweetpotato for its early maturity, resilience to stresses, and minimal input requirements. However, productivity remains low despite the effort of breeding programs to introduce new varieties. Low uptake of new varieties is partly attributed to previous focus by breeders on agronomic traits and much less on quality traits and the diverse preferences of men and women in sweetpotato value chains.

Method

To address this gap, breeders, food scientists, and social scientists (including gender specialists) systematically mainstreamed gender into the breeding program. This multidisciplinary approach, grounded in examining gender roles and their relationship with varietal and trait preferences, integrated important traits into product profiles.

Results

Building on earlier efforts of participatory plant breeding and participatory varietal selection, new interventions showed subtle but important gender differences in preferences. For instance, in a study for the RTBFoods project, women prioritized mealiness, sweetness, firmness and non-fibrous boiled roots. These were further subjected to a rigorous gender analysis using the G+ product profile query tool. The breeding pipelines then incorporated these gender-responsive priority quality traits, prompting the development of standard operating procedures to phenotype these traits.

Conclusion

Following an all-inclusive approach coupled with training of multidisciplinary teams involving food scientists, breeders, biochemists, gender specialists and social scientists, integration into participatory variety selection in Uganda enabled accentuation of women and men's trait preferences, contributing to clearer breeding targets. The research has positioned sweetpotato breeding to better respond to the varying needs and preferences of the users.

Using machine learning for image-based analysis of sweetpotato root sensory attributes

The sweetpotato breeding process involves assessing different phenotypic traits, such as the sensory attributes, to decide which varieties to progress to the next stage during the breeding cycle. Sensory attributes like appearance, taste, colour and mealiness are important for consumer acceptability and adoption of new varieties. Therefore, measuring these sensory attributes is critical to inform the selection of varieties during breeding. Current methods using a trained human panel enable screening of different sweetpotato sensory attributes. Despite this, such methods are costly and time-consuming, leading to low throughput, which remains the biggest challenge for breeders. In this paper, we describe an approach to apply machine learning techniques with image-based analysis to predict flesh-colour and mealiness sweetpotato sensory attributes. The developed models can be used as high-throughput methods to augment existing approaches for the evaluation of flesh-colour and mealiness for different sweetpotato varieties. The work involved capturing images of boiled sweetpotato cross-sections using the DigiEye imaging system, data pre-processing for background elimination and feature extraction to develop machine learning models to predict the flesh-colour and mealiness sensory attributes of different sweetpotato varieties. For flesh-colour the trained Linear Regression and Random Forest Regression models attained R 2 values of 0.92 and 0.87, respectively, against the ground truth values given by a human sensory panel. In contrast, the Random Forest Regressor and Gradient Boosting model attained R 2 values of 0.85 and 0.80, respectively, for the prediction of mealiness. The performance of the models matched the desirable R 2 threshold of 0.80 for acceptable comparability to the human sensory panel showing that this approach can be used for the prediction of these attributes with high accuracy. The machine learning models were deployed and tested by the sweetpotato breeding team at the International Potato Center in Uganda. This solution can automate and increase throughput for analysing flesh-colour and mealiness sweetpotato sensory attributes. Using machine learning tools for analysis can inform and quicken the selection of promising varieties that can be progressed for participatory evaluation during breeding cycles and potentially lead to increased chances of adoption of the varieties by consumers.