Data Fusion and Dimensionality Reduction for Pest Management in Pitahaya Cultivation
This study addresses the critical need for effective data fusion strategies in pest prediction for pitahaya (dragon fruit) cultivation in the Ecuadorian Amazon, where heterogeneous data sources—such as environmental sensors and chlorophyll measurements—offer complementary but fragmented insights. Cu...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Computation |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-3197/13/6/137 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849431987529449472 |
|---|---|
| author | Wilson Chango Mónica Mazón-Fierro Juan Erazo Guido Mazón-Fierro Santiago Logroño Pedro Peñafiel Jaime Sayago |
| author_facet | Wilson Chango Mónica Mazón-Fierro Juan Erazo Guido Mazón-Fierro Santiago Logroño Pedro Peñafiel Jaime Sayago |
| author_sort | Wilson Chango |
| collection | DOAJ |
| description | This study addresses the critical need for effective data fusion strategies in pest prediction for pitahaya (dragon fruit) cultivation in the Ecuadorian Amazon, where heterogeneous data sources—such as environmental sensors and chlorophyll measurements—offer complementary but fragmented insights. Current agricultural monitoring systems often fail to integrate these data streams, limiting early pest detection accuracy. To overcome this, we compared early and late fusion approaches using comprehensive experiments. Multidimensionality is a central challenge: the datasets span temporal (hourly sensor readings), spatial (plot-level chlorophyll samples), and spectral (chlorophyll reflectance) dimensions. We applied dimensionality reduction techniques—PCA, KPCA (linear, polynomial, RBF), t-SNE, and UMAP—to preserve relevant structure and enhance interpretability. Evaluation metrics included the proportion of information retained (score) and cluster separability (silhouette score). Our results demonstrate that early fusion yields superior integrated representations, with PCA and KPCA-linear achieving the highest scores (0.96 vs. 0.94), and KPCA-poly achieving the best cluster definition (silhouette: 0.32 vs. 0.31). Statistical validation using the Friedman test (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>χ</mi><mn>2</mn></msup></semantics></math></inline-formula> = 12.00, <i>p</i> = 0.02) and Nemenyi post hoc comparisons (<i>p</i> < 0.05) confirmed significant performance differences. KPCA-RBF performed poorly (score: 0.83; silhouette: 0.05), and although t-SNE and UMAP offered visual insights, they underperformed in clustering (silhouette < 0.12). These findings make three key contributions. First, early fusion better captures cross-domain interactions before dimensionality reduction, improving prediction robustness. Second, KPCA-poly offers an effective non-linear mapping suitable for tropical agroecosystem complexity. Third, our framework, when deployed in Joya de los Sachas, improved pest prediction accuracy by 12.60% over manual inspection, leading to more targeted pesticide use. This contributes to precision agriculture by providing low-cost, scalable strategies for smallholder farmers. Future work will explore hybrid fusion pipelines and sensor-agnostic models to extend generalizability. |
| format | Article |
| id | doaj-art-98193d287bb244429bb9c3bad25b44de |
| institution | Kabale University |
| issn | 2079-3197 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computation |
| spelling | doaj-art-98193d287bb244429bb9c3bad25b44de2025-08-20T03:27:28ZengMDPI AGComputation2079-31972025-06-0113613710.3390/computation13060137Data Fusion and Dimensionality Reduction for Pest Management in Pitahaya CultivationWilson Chango0Mónica Mazón-Fierro1Juan Erazo2Guido Mazón-Fierro3Santiago Logroño4Pedro Peñafiel5Jaime Sayago6Department of Systems and Computation, Pontifical Catholic University of Ecuador, Esmeraldas Campus PUCESE, Esmeraldas 080101, EcuadorFaculty of Engineering, University of Chimborazo UNACH, Riobamba 060101, EcuadorFaculty of Mechanical Engineering, Escuela Superior Politécnica de Chimborazo ESPOCH, Riobamba 060155, EcuadorFaculty of Business Administration, Escuela Superior Politécnica de Chimborazo ESPOCH, Riobamba 060155, EcuadorFaculty of Informatics and Electronics, Escuela Superior Politécnica de Chimborazo ESPOCH, Riobamba 060155, EcuadorEnvironmental Engineering, Escuela Superior Politécnica de Chimborazo ESPOCH, Riobamba 060155, EcuadorDepartment of Systems and Computation, Pontifical Catholic University of Ecuador, Esmeraldas Campus PUCESE, Esmeraldas 080101, EcuadorThis study addresses the critical need for effective data fusion strategies in pest prediction for pitahaya (dragon fruit) cultivation in the Ecuadorian Amazon, where heterogeneous data sources—such as environmental sensors and chlorophyll measurements—offer complementary but fragmented insights. Current agricultural monitoring systems often fail to integrate these data streams, limiting early pest detection accuracy. To overcome this, we compared early and late fusion approaches using comprehensive experiments. Multidimensionality is a central challenge: the datasets span temporal (hourly sensor readings), spatial (plot-level chlorophyll samples), and spectral (chlorophyll reflectance) dimensions. We applied dimensionality reduction techniques—PCA, KPCA (linear, polynomial, RBF), t-SNE, and UMAP—to preserve relevant structure and enhance interpretability. Evaluation metrics included the proportion of information retained (score) and cluster separability (silhouette score). Our results demonstrate that early fusion yields superior integrated representations, with PCA and KPCA-linear achieving the highest scores (0.96 vs. 0.94), and KPCA-poly achieving the best cluster definition (silhouette: 0.32 vs. 0.31). Statistical validation using the Friedman test (<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mi>χ</mi><mn>2</mn></msup></semantics></math></inline-formula> = 12.00, <i>p</i> = 0.02) and Nemenyi post hoc comparisons (<i>p</i> < 0.05) confirmed significant performance differences. KPCA-RBF performed poorly (score: 0.83; silhouette: 0.05), and although t-SNE and UMAP offered visual insights, they underperformed in clustering (silhouette < 0.12). These findings make three key contributions. First, early fusion better captures cross-domain interactions before dimensionality reduction, improving prediction robustness. Second, KPCA-poly offers an effective non-linear mapping suitable for tropical agroecosystem complexity. Third, our framework, when deployed in Joya de los Sachas, improved pest prediction accuracy by 12.60% over manual inspection, leading to more targeted pesticide use. This contributes to precision agriculture by providing low-cost, scalable strategies for smallholder farmers. Future work will explore hybrid fusion pipelines and sensor-agnostic models to extend generalizability.https://www.mdpi.com/2079-3197/13/6/137data fusionprecision agriculturepitahayadimensionality reductionpest predictionAmazonian crops |
| spellingShingle | Wilson Chango Mónica Mazón-Fierro Juan Erazo Guido Mazón-Fierro Santiago Logroño Pedro Peñafiel Jaime Sayago Data Fusion and Dimensionality Reduction for Pest Management in Pitahaya Cultivation Computation data fusion precision agriculture pitahaya dimensionality reduction pest prediction Amazonian crops |
| title | Data Fusion and Dimensionality Reduction for Pest Management in Pitahaya Cultivation |
| title_full | Data Fusion and Dimensionality Reduction for Pest Management in Pitahaya Cultivation |
| title_fullStr | Data Fusion and Dimensionality Reduction for Pest Management in Pitahaya Cultivation |
| title_full_unstemmed | Data Fusion and Dimensionality Reduction for Pest Management in Pitahaya Cultivation |
| title_short | Data Fusion and Dimensionality Reduction for Pest Management in Pitahaya Cultivation |
| title_sort | data fusion and dimensionality reduction for pest management in pitahaya cultivation |
| topic | data fusion precision agriculture pitahaya dimensionality reduction pest prediction Amazonian crops |
| url | https://www.mdpi.com/2079-3197/13/6/137 |
| work_keys_str_mv | AT wilsonchango datafusionanddimensionalityreductionforpestmanagementinpitahayacultivation AT monicamazonfierro datafusionanddimensionalityreductionforpestmanagementinpitahayacultivation AT juanerazo datafusionanddimensionalityreductionforpestmanagementinpitahayacultivation AT guidomazonfierro datafusionanddimensionalityreductionforpestmanagementinpitahayacultivation AT santiagologrono datafusionanddimensionalityreductionforpestmanagementinpitahayacultivation AT pedropenafiel datafusionanddimensionalityreductionforpestmanagementinpitahayacultivation AT jaimesayago datafusionanddimensionalityreductionforpestmanagementinpitahayacultivation |