Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
About

About

Master in Agricultural Engineering by the Faculty of Sciences of the University of Porto (FCUP) under the scope "Phenological forecasting models and pollen quality of Vitis vinifera L.", Mafalda Reis Pereira is currently a student in the Doctoral Program in Agricultural Sciences at FCUP. She is currently working in the field of "Detection and early identification of plant diseases caused by bacteria based on proximal detection in a precision agriculture perspective", having received a doctoral research grant from the Foundation for Science and Technology - FCT - with the reference SFRH/BD/146564/2019. Integrated on the Center for Industrial Robotics and Intelligent Systems (CRIIS), she is also a Member of the Advisory Group for Diversity and Inclusion at INESCTEC and a Member of the Network of Intercultural Ambassadors at INESCTEC. Interests: Precision Agriculture | Plant Pathology | Microbiology | Modeling | Data Science | Machine Learning | Spectroscopy

Interest
Topics
Details

Details

004
Publications

2022

Kiwi Plant Canker Diagnosis Using Hyperspectral Signal Processing and Machine Learning: Detecting Symptoms Caused by Pseudomonas syringae pv. actinidiae

Authors
Reis Pereira, M; Tosin, R; Martins, R; dos Santos, FN; Tavares, F; Cunha, M;

Publication
PLANTS-BASEL

Abstract
Pseudomonas syringae pv. actinidiae (Psa) has been responsible for numerous epidemics of bacterial canker of kiwi (BCK), resulting in high losses in kiwi production worldwide. Current diagnostic approaches for this disease usually depend on visible signs of the infection (disease symptoms) to be present. Since these symptoms frequently manifest themselves in the middle to late stages of the infection process, the effectiveness of phytosanitary measures can be compromised. Hyperspectral spectroscopy has the potential to be an effective, non-invasive, rapid, cost-effective, high-throughput approach for improving BCK diagnostics. This study aimed to investigate the potential of hyperspectral UV-VIS reflectance for in-situ, non-destructive discrimination of bacterial canker on kiwi leaves. Spectral reflectance (325-1075 nm) of twenty plants were obtained with a handheld spectroradiometer in two commercial kiwi orchards located in Portugal, for 15 weeks, totaling 504 spectral measurements. Several modeling approaches based on continuous hyperspectral data or specific wavelengths, chosen by different feature selection algorithms, were tested to discriminate BCK on leaves. Spectral separability of asymptomatic and symptomatic leaves was observed in all multi-variate and machine learning models, including the FDA, GLM, PLS, and SVM methods. The combination of a stepwise forward variable selection approach using a support vector machine algorithm with a radial kernel and class weights was selected as the final model. Its overall accuracy was 85%, with a 0.70 kappa score and 0.84 F-measure. These results were coherent with leaves classified as asymptomatic or symptomatic by visual inspection. Overall, the findings herein reported support the implementation of spectral point measurements acquired in situ for crop disease diagnosis.

2018

Comparison of pollen quality in Vitis vinifera L. cultivars

Authors
Pereira, MR; Ribeiro, H; Cunha, M; Abreu, I;

Publication
SCIENTIA HORTICULTURAE

Abstract
Pollen quality of 15 cultivars of Vitis vinifera L. was studied in this work. Pollen viability was tested by the fluorochromatic reaction and germination was analyzed by in vitro assays, using two different media. Differences among cultivars in the number of pollen apertures were observed under light microscope. All the cultivars studied showed a higher percentage of tricolporated pollen, however, pollen grains containing one, two or four apertures were also observed. The cultivar Loureiro was the one with the higher percentage of pollen grains with four apertures (3.8%) and Touriga Nacional presented 100% of tricolporated pollen grains. The viability analysis showed that 13 cultivars presented values higher than 50%, with 8 cultivars reaching values above 75%. The pollen germination rates vary greatly for the grapevine cultivars studied, three cultivars show low values of germination (under 14%) in the two media tested, which were Touriga Nacional, Cabernet Franc, and Cabernet Sauvignon while others presented high values of germination like Casteldo, Loureiro, Malbec and Petit Verdot. No significant statistical differences between the percentages of germination in the two media studied were found for the majority of cultivars analyzed.

2018

Predicting the flowering date of Portuguese grapevine varieties using temperature-based phenological models: a multi-site approach

Authors
Pereira, MR; Ribeiro, H; Abreu, I; Eiras Dias, J; Mota, T; Cunha, M;

Publication
JOURNAL OF AGRICULTURAL SCIENCE

Abstract
Phenological models for predicting the grapevine flowering were tested using phenological data of 15 grape varieties collected between 1990 and 2014 in Vinhos Verdes and Lisbon Portuguese wine regions. Three models were tested: Spring Warming (Growing Degree Days - GDD model), Spring Warming modified using a triangular function - GDD triangular and UniFORC model, which considers an exponential response curve to temperature. Model estimation was performed using data on two grape varieties (Loureiro and Fernao Pires), present in both regions. Three dates were tested for the beginning of heat unit accumulation (t(0)( )date): budburst, 1 January and 1 September. The best overall date was budburst. Furthermore, for each model parameter, an intermediate range of values common for the studied regions was estimated and further optimized to obtain one model that could he used for a diverse range of grape varieties in both wine regions. External validation was performed using an independent data set from 13 grape varieties (seven red and six white), different from the two used in the estimation step. The results showed a high coefficient of determination (R-2 : 0.59-0.89), low Root Mean Square Error (RMSE: 3-7 days) and Mean Absolute Deviation (MAD: 2-6 days) between predicted and observed values. The UniFORC model overall performed slightly better than the two GDD models, presenting higher R-2 (0.75) and lower RMSE (4.55) and MAD (3.60). The developed phenological models presented good accuracy when applied to several varieties in different regions and can be used as a predictor tool of flowering date in Portugal.