Dylan Warren Raffa

Dr. Dylan Warren Raffa


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 February 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MPMarko Pavlovic
Marko Pavlovic
SISlobodan Ilic
Slobodan Ilic
NRNebojša M. Ralević
Nebojša M. Ralević
NANenad Antonic
Nenad Antonic
DRDylan Warren Raffa
Dylan Warren Raffa
DCDubravko Culibrk
Dubravko Culibrk
Monitoring soil organic carbon (SOC) typically assumes conducting a labor-intensive soil sampling campaign, followed by laboratory testing, which is both expensive and impractical for generating useful, spatially continuous data products. The present study leverages the power of machine learning (ML) and, in particular, deep neural networks (DNNs) for segmentation, as well as satellite imagery, to estimate the SOC remotely. We propose a new two-stage pipeline for remote SOC estimation, which relies on using a DNN trained to classify land cover to perform feature extraction, while the SOC estimation is performed by a different ML model. The first stage is an image segmentation DNN with the U-Net architecture, which is trained to estimate the land cover for an observed geographical region, based on multi-spectral images taken by the Sentinel-2 satellite constellation. This estimator is subsequently used to extract the latent feature vector for each of the output pixels, by rolling back from the output (dense) layer of the U-Net and accessing the last available convolutional layer of the same dimension as our desired output. The second stage is trained on a set of feature vectors extracted at the coordinates for which manual SOC measurements exist. We tested a variety of ML models and report on their performance. Using the best extremely randomized trees model, we generated a spatially continuous map of SOC estimations for the region of Tuscany, in Italy, with a resolution of 10 m, to share with the researchers as a means of validating the results and to demonstrate the efficiency of the proposed approach, which can can easily be scaled to create a global continuous SOC map.

29 January 2023 in Microorganisms
Verified
Journal Article
Open access
PDF file
ATAlessandra Trinchera
Alessandra Trinchera
DRDylan Warren Raffa
Dylan Warren Raffa
Weeds have always been considered an insidious enemy, capable of reducing crop production. Conversely, the agroecological vision attributes a key role to the spontaneous flora in promoting plant diversity and belowground interactions, which may improve the ecological performance of agroecosystems. We summarized the literature on the weeds’ arbuscular–mycorrhizae (AM) interaction and we analyzed evidence on the: (i) AM suppressive/selective effect on weed communities; (ii) effect of weeds on AM colonization, and (iii) positive role of AM-supporting weeds on forming shared mycorrhizal hyphal connections in agroecosystems. While some authors conceptualized AM as a weed control tool, others underlined their selective effect on weed communities. Recent studies suggest that AM-host weeds can participate in the development of a common mycorrhizal mycelial network (MMN) among different plants species. Nevertheless, direct evidence of the actual exchange of nutrients and C between coexisting plants through MMN in agroecosystems is missing. Although the effect of agricultural practices on plant community-AM interactions are complex, more conservative farming management seems to foster AM populations. Future studies should focus on: (i) field studies, (ii) weed communities and their traits, rather than on the most abundant species, and (iii) the use of advanced analytical techniques, able to monitor MMN development and functionality.

18 December 2024 in Agronomy
Verified
Journal Article
Open access
PDF file
MDModupe Olufemi Doyeni
Modupe Olufemi Doyeni
Gražina KadžienėGražina Kadžienė
Gražina Kadžienė
SPSimona Pranaitiene
Simona Pranaitiene
Alvyra ŠlepetienėAlvyra Šlepetienė
Alvyra Šlepetienė
ASAida Skersiene
Aida Skersiene
Skaidrė SupronienėSkaidrė Supronienė
Skaidrė Supronienė
Continuous agricultural activities lead to soil organic carbon (SOC) depletion, and agroecological intensification practices (i.e., reduced soil disturbance and crop diversification) have been suggested as strategies to increase SOC storage. The study aims to assess the effect of agroecological intensification levels (lower (T1) and highest (T2)) on the soil C pool and aggregate stability and validate the correlation between different variables compared to the control (lowest/none (T3), where agroecological intensification was not applied. The C-stock, soil microbial biomass carbon (SMB-C), SOC, water extractable organic carbon (WEOC) in bulk soil, fine and coarse soil aggregates, and water-stable aggregates (WSA) were measured during maximum nutrient uptake in plants under diversified agroecological practices across different environmental conditions (core sites: Italy (CS1), France (CS2), Denmark (CS4), Spain (CS5), Netherlands (CS6), Lithuania (CS7), Turkey (CS8), and Belgium (CS9)). The soil aggregate stability varied among the CSs and treatments. At sites CS7 and CS9, WSA was higher in T1 and T2 compared to the control; a similar trend was observed at other sites, except CS1. SMB-C differed among the core sites, with the lowest value obtained in CS5 (52.3 μg g−1) and the highest in CS6 (455.1 μg g−1). The highest average contents of SOC and WEOC were obtained in bulk soil at CS2 (3.1 % and 0.3 g kg−1 respectively). Positive and statistically significant (p < 0.001) correlations were detected among all variables tested with SOC in bulk soil and WSA. This study demonstrates the significance of agroecological practices in improving soil carbon stock and optimizing plant–soil–microbe interactions.

17 May 2026 in Agronomy
Verified
Journal Article
Open access
PDF file
DRDylan Warren Raffa
Dylan Warren Raffa
LPLuisa del Piano
Luisa del Piano
Eugenio CozzolinoEugenio Cozzolino
Eugenio Cozzolino
TETommaso Enotrio
Tommaso Enotrio
MQMarco Quattrucci
Marco Quattrucci
LMLuigi Morra
Luigi Morra
Tobacco (Nicotiana tabacum L.) is an industrial crop cultivated worldwide with intensive management systems that include continuous cropping, conventional tillage and high use of agrochemicals. The increasing concerns about environmental and economic sustainability call for innovative practices to maintain yield while managing weeds and enhancing soil fertility. Our research investigated the effect of green manure or cover crops coupled with minimum tillage on Kentucky tobacco production and the level of control of weeds. Six integrated management systems were tested in a four-year trial in Tuscany, Italy: (TS1) conventional farming management as defined above; (TS2) reduction in fertilizers and compost application; (TS3) rotation of tobacco–leguminous green manure and reduction in fertilizers; (TS4) rotation of tobacco–leguminous green manure and compost application without fertilizers; (TS5) rotation of tobacco–mixture of cover crops, minimum tillage before tobacco transplant, reduction in fertilizers; (TS6) as in TS5 but with a compost amendment addition. The different farming practices represented an ecological filter for the weed communities. The combination of conventional tillage, compost application and green manure was sufficient to control weed development. On the other hand, cover crop termination via roller crimper and minimum tillage did not reduce weed pressure, thereby negatively affecting tobacco production. Further studies are needed to improve the effectiveness of mulching and minimal tillage on weed levels not detrimental to tobacco development. It would be advisable to alternate different weed management strategies to prevent community specialization, mitigate negative effects on crops and enhance biodiversity at the farm scale.