The mistletoe Phoradendron velutinum (P. velutinum) is a pest that spreads rapidly and uncontrollably in Mexican forests, becoming a serious problem since it is a cause of the decline of 23.3 million hectares of conifers and broadleaves in the country. The lack of adequate phytosanitary control has negative social, economic, and environmental impacts. However, pest management is a challenging task due to the difficulty of early detection for proper control of mistletoe infestations. Automating the detection of this pest is important due to its rapid spread and the high costs of field identification tasks. This paper presents a Genetic Programming (GP) approach for the automatic design of an algorithm to detect mistletoe using multispectral aerial images. Our study area is located in a conservation area of Mexico City, in the San Bartolo Ameyalco community. Images of 148 hectares were acquired by means of an Unmanned Aerial Vehicle (UAV) carrying a sensor sensitive to the R, G, B, red edge, and near-infrared bands, and with an average spatial resolution of less than 10 cm per pixel. As a result, it was possible to obtain an algorithm capable of classifying mistletoe P. velutinum at its flowering stage for the specific case of the study area in conservation area with an Overall Accuracy (OA) of 96% and a value of fitness function based on weighted Cohen’s Kappa ($k_w$) equal to 0.45 in the test data set. Additionally, our method’s performance was compared with two traditional image classification methods; in the first, a classical spectral index, named Intensive Pigment Index of Structure 2 (SIPI2), was considered for the detection of P. velutinum. The second method considers the well-known Support Vector Machine classification algorithm (SVM). We also compare the accuracy of the best GP individual with two additional indices obtained during the solution analysis. According to our experimental results, our GP-based algorithm outperforms the results obtained by the aforementioned methods for the identification of P. velutinum.

Registration of remote sensing images has been approached using different strategies; one of the most popular is based on similarity measures. There are different measures of similarity in the literature: Normalized Cross-Correlation (NCC), Mutual Information (MI), etc. Normalized Mutual Information (NMI) has received the most attention in image processing; among the most important limitations are its high computational cost and lack of robustness to strong radiometric changes. For this reason, in this work, we introduce a co-registration approach based on the Histogram Kernel Predictability (HKP). This formulation reduces numerical errors and requires less computing time in comparison to NMI. To the best of our knowledge, this is the first work for registering any remote sensing images by using HKP. Additionally, we propose to use an algorithm based on meta-heuristics called Evolutionary Centers Algorithm (ECA), which allows having fewer iterations to solve the registration problem. In addition, we incorporate a parallelization scheme that permits reducing processing times. The results show that our proposal can solve co-registration problems that the NMI cannot solve while obtaining competitive computational times and registration errors comparable with other existing works in the literature. The HKP approach solves most of all the transformations of a set of simulated registration problems, while the NMI, in some cases, only solves half of the registration problems. Moreover, we compare our approach with feature-based methods in real datasets. This research presents an alternative to remote sensing problems where MI has traditionally been used.

In recent years, Deep Learning (DL) has gained popularity among the Re-mote Sensing (RS) and Computer Vision communities to address social-environmental problems. In particular, DL has shown impressive performance. However, some members of the RS community are reluctant to adopt black-box solutions because they have a legitimate interest in understanding how models work and what they can tell us about the phenomena they model. In this case, Genetic Programming (GP) seems a good option. However, due to the GP’s bloat problem, in most cases the best GP solutions are large,complex, and also very difficult to interpret. In this work, we performed a comparative analysis between three effective state-of-the-art mechanisms for simplifying GP individuals, and two proposals we made based on the Rademacher model complexity measure due to its ability to reflect both the performance and the complexity/simplicity of the models. These experiments were run for two different tasks, first, to solve the symbolic regression problem of the quartic function because it is a common benchmark in the GP community, and for the automatic design of an algorithm to identify mistletoe in multispectral aerial images. As a result, it was verified that the proposed simplification methods generate smaller individuals, less complex but with a high generalization capacity that opens the door to the interpretability of real-world problems. This work also provides novel tools for controlling the blob problem and developing interpretable models.

This paper proposes a novel method for automatically designing lightweight Convolutional Neural Network (CNN) architectures. (1) Background: Automated remote sensing for vegetation monitoring faces challenges from structural complexity and cluttered backgrounds. For detecting parasitic Phoradendron velutinum infestations, existing vision frameworks rely on handcrafted, overparameterized CNNs, limiting deployment on localized edge computing platforms. (2) Methods: To address this efficiency-accuracy trade-off, a two-phase hybrid multi-objective Neural Architecture Search (NAS) strategy is implemented. First, the Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D) minimizes classification error and the number of trainable parameters. Second, an Iterated Local Search (ILS) metaheuristic refines promising non-dominated solutions. The approach was evaluated using cost-effective aerial RGB imagery, processing a balanced dataset of 5000 patches ($64\times 64$ pixels) under a rigorous three-way data partition to prevent data leakage. (3) Results: The discovered 10-layer CNN topology achieved high feature-extraction efficiency. On the unseen testing set, the model yielded an Accuracy and F1-Score of $0.979$, a Precision of $0.982$, a Recall of $0.976$, and a Jaccard Index of $0.958$, outperforming the compared models. Operating with only 2040 trainable parameters, the optimized architecture establishes a highly viable paradigm for real-time digital image processing on hardware-constrained monitoring devices.

From the Environmental and Remote Sensing community, the need for AI models that are accurate but also interpretable is increasing. However, usually Deep and Machine Learning techniques are uninterpretable. In this study, we propose to use Genetic Programming (GP) because of the readable nature of candidate solutions, like arithmetic expressions, for the detection of Phoradendron velutinum on five-band multispectral aerial images. Nevertheless, GP suffers from the bloat problem, which is the uncontrolled size growth of the candidate solutions, making them uninterpretable. With the aim of obtaining smaller, simpler, and interpretable solutions, we propose to test five GP simplification methods. The methods considered were Gws 25, Pruning 2%, and Gws 25 and Pruning 2% together. In addition, we proposed two novel approaches based on the Rademacher Complexity (RC) metric called Rademacher and Fit Rademacher. These strategies were evaluated over 30 independent runs with five-fold cross-validation on 250 images of 300 × 300 pixels. The folds group tiles by source frame, so the reported metrics are within-site estimates. The Fit Rademacher method achieved a 54% reduction in the average tree size (22 Fit Rademacher vs. 48 nodes Plain GP) and the highest Recall among all methods (0.566), trading precision and overall agreement for that gain: relative to Plain GP, its test ${\kappa }_w$ falls from 0.448 to 0.402, its F1 from 0.499 to 0.399, and its precision from 0.498 to 0.307. Among the solutions found, GP-VRI (GP Velutinum Red Index) is a compact expression that was algebraically reduced from 25 to 14 nodes, that uses only the Red (650 nm) and Blue (450 nm) bands, and whose structure is biochemically plausible in light of the flavanone, carotenoid, and chlorophyll content reported for P. velutinum. A second solution, GP-VSDI (GP Velutinum Spectral Difference Index), was algebraically reduced from 28 to 24 nodes and uses the same two bands: the $R-B$ difference appears twice in its denominator, while its numerator reduces to a constant factor where $R\ge 2B$, independently confirming that this band combination is the most informative for distinguishing P. velutinum from its background on this dataset. These results establish RC-guided GP simplification as a knowledge extraction mechanism in the remote sensing problem studied here, producing models compact enough to be inspected and assessed by domain experts, whose structure is physically consistent with the known spectral behavior of the target species. The methodological contribution is the pair of RC-guided operators; the detection framework and dataset are inherited from previous work.