Isabel Luisa Castillejo-González
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Isabel Luisa Castillejo-González has a total of 36 co-authors. Here are the top co-authors by number of shared publications:
- Alfonso García-Ferrer
Department of Graphic Engineering and Geomatics, Campus de Rabanales, University of Cordoba, 14071 Córdoba, Spain
7 shared publications - Francisco Javier Mesas-Carrascosa
Department of Graphic Engineering and Geomatics, Universidad de Córdoba, Campus de Rabanales, 14071 Córdoba, Spain
5 shared publications - Francisca López-Granados
Department of Crop Protection, Institute for Sustainable Agriculture (IAS), Spanish National Research Council (CSIC), 14004 Córdoba, Spain
4 shared publications - Jose Manuel Peña
Institute of Agricultural Sciences (ICA), Spanish National Research Council (CSIC), Madrid, Spain
4 shared publications Manuel Sánchez de la Orden
4 shared publications- Montserrat Jurado-Expósito
Institute for Sustainable Agriculture, CSIC
4 shared publications
Latest Publications
- Open Access
Machine Learning-Based Prediction of Stem Water Potential in Olive Orchards Using PlanetScope Imagery and Meteorological Data
Accurate assessment of water status in woody crops is essential for optimizing irrigation management, particularly under Mediterranean conditions characterized by high spatial and temporal variability. Traditional field-based stem water potential measurements are reliable but limited for large-scale operational applications. In this study, a supervised machine learning approach based on Extreme Gradient Boosting was developed to estimate stem water potential in Mediterranean olive orchards by integrating high-resolution PlanetScope multispectral imagery with meteorological variables describing atmospheric evaporative demand. The model was trained and evaluated using a dataset comprising 1628 measurements, curated from 1856 measurements collected during 2021–2025 after temporal matching and quality-control filtering, and 128 predictive features: 44 PlanetScope-derived spectral features and 84 meteorological predictors evaluated across six temporal positions (t0–t5). Model performance was assessed using cross-validation. The model achieved a coefficient of determination of 0.84, a root mean square error of 0.27, and a mean absolute error of 0.21. Air temperature, solar radiation, and reference evapotranspiration were the most influential predictors, while spectral information captured complementary effects related to canopy structure, vegetative vigor, and accumulated physiological responses. Furthermore, the combined use of spectral indices and PlanetScope base-band reflectance values was associated with an approximately 30% lower RMSE than that reported in previous approaches.
Open AccessMachine Learning-Based Prediction of Stem Water Potential in Olive Orchards Using PlanetScope Imagery and Meteorological Data
Accurate assessment of water status in woody crops is essential for optimizing irrigation management, particularly under Mediterranean conditions characterized by high spatial and temporal variability. Traditional field-based stem water potential measurements are reliable but limited for large-scale operational applications. In this study, a supervised machine learning approach based on Extreme Gradient Boosting was developed to estimate stem water potential in Mediterranean olive orchards by integrating high-resolution PlanetScope multispectral imagery with meteorological variables describing atmospheric evaporative demand. The model was trained and evaluated using a dataset comprising 1628 measurements, curated from 1856 measurements collected during 2021–2025 after temporal matching and quality-control filtering, and 128 predictive features: 44 PlanetScope-derived spectral features and 84 meteorological predictors evaluated across six temporal positions (t0–t5). Model performance was assessed using cross-validation. The model achieved a coefficient of determination of 0.84, a root mean square error of 0.27, and a mean absolute error of 0.21. Air temperature, solar radiation, and reference evapotranspiration were the most influential predictors, while spectral information captured complementary effects related to canopy structure, vegetative vigor, and accumulated physiological responses. Furthermore, the combined use of spectral indices and PlanetScope base-band reflectance values was associated with an approximately 30% lower RMSE than that reported in previous approaches.
- Open Access
- 3 August 2026
- Published by MDPI AG in Preprints.org
Machine Learning-Based Prediction of Stem Water Potential in Olive Orchards Using PlanetScope Imagery and Meteorological Data
Accurate assessment of water status in woody crops is essential for optimizing irrigation management, particularly under Mediterranean conditions characterized by both high spatial and temporal variability. Traditional field-based measurements of stem water potential are reliable but present limitations for large-scale operational applications. In this study, a supervised machine learning approach based on Extreme Gradient Boosting was developed to estimate this metric in Mediterranean olive orchards by integrating high-resolution PlanetScope multispectral imagery with meteorological variables describing atmospheric evaporative demand. The model has been trained and evaluated using a dataset comprising 1,321 field-based stem water potential measurements collected during the 2021–2025 period, together with 129 predictive features, including PlanetScope-derived spectral bands and vegetation indices, as well as meteorological predictors. The results demonstrate a high level of accuracy, achieving a coefficient of determination of 0.84, a root mean square error of 0.27, and a mean absolute error of 0.21. Variable importance analysis indicates that air temperature, solar radiation, and reference evapotranspiration are the most influential predictors, while spectral information acts as a modulating factor incorporating effects related to canopy structure, vegetative vigor, and accumulated physiological responses. Furthermore, the combined use of spectral indices and base band reflectance values from PlanetScope, particularly those related to Photochemical Reflectance Index and Near Infrared, consistently improving model accuracy of 30% from previous proposed algorithms.
- 3 August 2026
- Published by MDPI AG in Preprints.org
Open AccessMachine Learning-Based Prediction of Stem Water Potential in Olive Orchards Using PlanetScope Imagery and Meteorological Data
Accurate assessment of water status in woody crops is essential for optimizing irrigation management, particularly under Mediterranean conditions characterized by both high spatial and temporal variability. Traditional field-based measurements of stem water potential are reliable but present limitations for large-scale operational applications. In this study, a supervised machine learning approach based on Extreme Gradient Boosting was developed to estimate this metric in Mediterranean olive orchards by integrating high-resolution PlanetScope multispectral imagery with meteorological variables describing atmospheric evaporative demand. The model has been trained and evaluated using a dataset comprising 1,321 field-based stem water potential measurements collected during the 2021–2025 period, together with 129 predictive features, including PlanetScope-derived spectral bands and vegetation indices, as well as meteorological predictors. The results demonstrate a high level of accuracy, achieving a coefficient of determination of 0.84, a root mean square error of 0.27, and a mean absolute error of 0.21. Variable importance analysis indicates that air temperature, solar radiation, and reference evapotranspiration are the most influential predictors, while spectral information acts as a modulating factor incorporating effects related to canopy structure, vegetative vigor, and accumulated physiological responses. Furthermore, the combined use of spectral indices and base band reflectance values from PlanetScope, particularly those related to Photochemical Reflectance Index and Near Infrared, consistently improving model accuracy of 30% from previous proposed algorithms.
- Open Access
- 27 September 2025
- Published by Elsevier in Journal of Environmental Management
- Vol. 394, 127439
Optimizing water management: Identifying strategies to enhance irrigation efficiency under drought conditions
- 27 September 2025
- Published by Elsevier in Journal of Environmental Management
- Vol. 394, 127439
Open AccessOptimizing water management: Identifying strategies to enhance irrigation efficiency under drought conditions
- Open Access
- 21 May 2025
- Published by Wiley in Conservation Biology
- Vol. 39 (4) , e70067
Habitat dynamics of flagship species for conservation prioritization in southern Europe
Biodiversity loss is accelerating due to human actions, and decision‐making for conservation needs to be streamlined. Ex situ biodiversity modeling and monitoring based on satellite time‐series data could be an affordable and cost‐efficient tool for improving the prioritization of conservation areas. We developed a set of dynamic indicators for conservation prioritization based on a habitat suitability index (HSI) trend analysis of 6 flagship species (two vascular plants, bird, amphibian, reptile, and mammal) over 19 years (2001–2019) in Andalucía (southern Spain). The HSI models were derived from ecological niche models (MaxEnt) and satellite time‐series data (MODIS) as predictors. Based on the annual HSI models of all species and using the spatial conservation prioritization tool Marxan, we derived interannual dynamic indicators of habitat quality for conservation prioritization. Overall, models showed a generalized habitat regression. The best predictors of habitat quality were related to vegetation composition and structure (land cover), climate (land surface temperature), and energy balance (evapotranspiration), matching with the ecology of climate (such as Abies pinsapo ) or vegetation‐dependent (such as Alytes dickhilleni ) species. Marxan identified interannual dynamics for the priority areas outside and inside protected areas. Interannual variation in habitat quality led to shifting conservation priorities across Andalucia from 2001 to 2019. Only 10.5% of the region and 20% of protected areas showed high spatial stability. Stable zones appeared both inside and outside protected areas. The south and northeast consistently exhibited high‐priority regions. The legacy indicator highlighted areas of historical importance that have since declined in importance. New high‐value areas emerged in the south. Static and dynamic approaches to conservation planning differed significantly. Many areas prioritized in 2019 alone ranked lower when long‐term trends were considered. Our multiscale method underscores the need to integrate temporal dynamics into effective conservation strategies to achieve long‐term conservation objectives in an efficient way.
- 21 May 2025
- Published by Wiley in Conservation Biology
- Vol. 39 (4) , e70067
Open AccessHabitat dynamics of flagship species for conservation prioritization in southern Europe
Biodiversity loss is accelerating due to human actions, and decision‐making for conservation needs to be streamlined. Ex situ biodiversity modeling and monitoring based on satellite time‐series data could be an affordable and cost‐efficient tool for improving the prioritization of conservation areas. We developed a set of dynamic indicators for conservation prioritization based on a habitat suitability index (HSI) trend analysis of 6 flagship species (two vascular plants, bird, amphibian, reptile, and mammal) over 19 years (2001–2019) in Andalucía (southern Spain). The HSI models were derived from ecological niche models (MaxEnt) and satellite time‐series data (MODIS) as predictors. Based on the annual HSI models of all species and using the spatial conservation prioritization tool Marxan, we derived interannual dynamic indicators of habitat quality for conservation prioritization. Overall, models showed a generalized habitat regression. The best predictors of habitat quality were related to vegetation composition and structure (land cover), climate (land surface temperature), and energy balance (evapotranspiration), matching with the ecology of climate (such as Abies pinsapo ) or vegetation‐dependent (such as Alytes dickhilleni ) species. Marxan identified interannual dynamics for the priority areas outside and inside protected areas. Interannual variation in habitat quality led to shifting conservation priorities across Andalucia from 2001 to 2019. Only 10.5% of the region and 20% of protected areas showed high spatial stability. Stable zones appeared both inside and outside protected areas. The south and northeast consistently exhibited high‐priority regions. The legacy indicator highlighted areas of historical importance that have since declined in importance. New high‐value areas emerged in the south. Static and dynamic approaches to conservation planning differed significantly. Many areas prioritized in 2019 alone ranked lower when long‐term trends were considered. Our multiscale method underscores the need to integrate temporal dynamics into effective conservation strategies to achieve long‐term conservation objectives in an efficient way.
- Open Access
- 27 December 2024
- Published by Universitat Politecnica de Valencia in EGA Revista de Expresión Gráfica Arquitectónica
- Vol. 29 (52) , 216-227
Análisis de la plaza octogonal de San José de Aguilar de la Frontera (Córdoba): geometría y encaje urbano
La plaza octogonal de San José es uno de los escasos ejemplos de plazas programadas neoclásicas de planta poligonal de principios del siglo XIX. En este artículo se analiza la evolución urbana del municipio de Aguilar de la Frontera (Córdoba) hasta la construcción de este conjunto histórico-artístico. A partir de ahí se estudian los aspectos físicos del entorno, el origen del proyecto, su encaje urbano, las características de su diseño, la geometría y la ejecución final de un elemento arquitectónico singular que se construye en una época especialmente conflictiva.
- 27 December 2024
- Published by Universitat Politecnica de Valencia in EGA Revista de Expresión Gráfica Arquitectónica
- Vol. 29 (52) , 216-227
Open AccessAnálisis de la plaza octogonal de San José de Aguilar de la Frontera (Córdoba): geometría y encaje urbano
La plaza octogonal de San José es uno de los escasos ejemplos de plazas programadas neoclásicas de planta poligonal de principios del siglo XIX. En este artículo se analiza la evolución urbana del municipio de Aguilar de la Frontera (Córdoba) hasta la construcción de este conjunto histórico-artístico. A partir de ahí se estudian los aspectos físicos del entorno, el origen del proyecto, su encaje urbano, las características de su diseño, la geometría y la ejecución final de un elemento arquitectónico singular que se construye en una época especialmente conflictiva.
- Open Access
Detection of Planting Systems in Olive Groves Based on Open-Source, High-Resolution Images and Convolutional Neural Networks
This paper aims to evaluate whether an automatic analysis with deep learning convolutional neural networks techniques offer the ability to efficiently identify olive groves with different intensification patterns by using very high-resolution aerial orthophotographs. First, a sub-image crop classification was carried out. To standardize the size and increase the number of samples of the data training (DT), the crop images were divided into mini-crops (sub-images) using segmentation techniques, which used a different threshold and stride size to consider the mini-crop as suitable for the analysis. The four scenarios evaluated discriminated the sub-images efficiently (accuracies higher than 0.8), obtaining the largest sub-images (H = 120, W = 120) for the highest average accuracy (0.957). The super-intensive olive plantings were the easiest to classify for most of the sub-image sizes. Nevertheless, although traditional olive groves were discriminated accurately, too, the most difficult task was to distinguish between the intensive plantings and the traditional ones. A second phase of the proposed system was to predict the crop at farm-level based on the most frequent class detected in the sub-images of each crop. The results obtained at farm level were slightly lower than at the sub-images level, reaching the highest accuracy (0.826) with an intermediate size image (H = 80, W = 80). Thus, the convolutional neural networks proposed made it possible to automate the classification and discriminate accurately among traditional, intensive, and super-intensive planting systems.
Open AccessDetection of Planting Systems in Olive Groves Based on Open-Source, High-Resolution Images and Convolutional Neural Networks
This paper aims to evaluate whether an automatic analysis with deep learning convolutional neural networks techniques offer the ability to efficiently identify olive groves with different intensification patterns by using very high-resolution aerial orthophotographs. First, a sub-image crop classification was carried out. To standardize the size and increase the number of samples of the data training (DT), the crop images were divided into mini-crops (sub-images) using segmentation techniques, which used a different threshold and stride size to consider the mini-crop as suitable for the analysis. The four scenarios evaluated discriminated the sub-images efficiently (accuracies higher than 0.8), obtaining the largest sub-images (H = 120, W = 120) for the highest average accuracy (0.957). The super-intensive olive plantings were the easiest to classify for most of the sub-image sizes. Nevertheless, although traditional olive groves were discriminated accurately, too, the most difficult task was to distinguish between the intensive plantings and the traditional ones. A second phase of the proposed system was to predict the crop at farm-level based on the most frequent class detected in the sub-images of each crop. The results obtained at farm level were slightly lower than at the sub-images level, reaching the highest accuracy (0.826) with an intermediate size image (H = 80, W = 80). Thus, the convolutional neural networks proposed made it possible to automate the classification and discriminate accurately among traditional, intensive, and super-intensive planting systems.
- Open Access
- 21 May 2021
- Published by MDPI AG in Sustainability
- Vol. 13 (11) , 5791
Strengthening Efforts to Protect and Safeguard the Industrial Cultural Heritage in Montilla-Moriles (PDO). Characterisation of Historic Wineries
Industrial heritage is linked to the cultural processes that human society sets through the traces from the past. The conservation and dissemination of this industrial–cultural heritage are crucial for sustainable urban development, and positively influences the transition to resilient and sustainable cities. The wine industry around Montilla has suffered as a result of a sharp reduction of the vineyard area in the last 25 years. Wineries, as one of the historic typologies of wine-making facilities in the Montilla-Moriles Protected Designation of Origin (PDO), as well as their materials and construction techniques, are a reference in the agricultural landscape of Montilla. Many historic wineries are the result of the abandonment and cessation of the wine industry. These buildings are linked to the agrarian activity in this area, mostly wine-making, although in some cases, they coexist with similar production processes, such as milling the fruit of the olive grove. This research characterises and analyses four historic wineries in the Montilla-Moriles PDO, which represent an example of architecture in the wine-making transformation during the 19th–20th centuries. This manuscript contributes to the attainment of some objectives set in one of the Sustainable Development Goals (SDGs), protecting and disseminating the industrial cultural heritage in Montilla-Moriles.
- 21 May 2021
- Published by MDPI AG in Sustainability
- Vol. 13 (11) , 5791
Open AccessStrengthening Efforts to Protect and Safeguard the Industrial Cultural Heritage in Montilla-Moriles (PDO). Characterisation of Historic Wineries
Industrial heritage is linked to the cultural processes that human society sets through the traces from the past. The conservation and dissemination of this industrial–cultural heritage are crucial for sustainable urban development, and positively influences the transition to resilient and sustainable cities. The wine industry around Montilla has suffered as a result of a sharp reduction of the vineyard area in the last 25 years. Wineries, as one of the historic typologies of wine-making facilities in the Montilla-Moriles Protected Designation of Origin (PDO), as well as their materials and construction techniques, are a reference in the agricultural landscape of Montilla. Many historic wineries are the result of the abandonment and cessation of the wine industry. These buildings are linked to the agrarian activity in this area, mostly wine-making, although in some cases, they coexist with similar production processes, such as milling the fruit of the olive grove. This research characterises and analyses four historic wineries in the Montilla-Moriles PDO, which represent an example of architecture in the wine-making transformation during the 19th–20th centuries. This manuscript contributes to the attainment of some objectives set in one of the Sustainable Development Goals (SDGs), protecting and disseminating the industrial cultural heritage in Montilla-Moriles.
- Open Access
- 31 August 2020
- Published by MDPI AG in Sustainability
- Vol. 12 (17) , 7104
The Church Tower of Santiago Apóstol in Montilla: An Eco-Sustainable Rehabilitation Proposal
Is it possible to carry out eco-sustainable rehabilitations on specially protected buildings? This is the main question and starting point for this research. We will use the tower of the Church of “Santiago Apóstol” in Montilla as a case study; with its most remote antecedents in the 15th century, it is an emblematic building of one of the most important cities in the Cordovan countryside and is listed as an Asset of Cultural Interest (Bien de Interés Cultural or BIC) as of 2001. The application of eco-efficiency criteria in the rehabilitation of this type of building might stimulate the reactivation of the construction sector in the rural area, positively impacting the promotion of a circular economy. To this end, a general methodology has been established for carrying out eco-sustainable renovations on this type of building, which defines indicators for evaluating the eco-sustainability of such interventions. This methodology is applied to the case study of this important building in Montilla to ensure that a feasible intervention has been proposed, aligned with three basic pillars of sustainability that considers its environmental, economic, and social impact.
- 31 August 2020
- Published by MDPI AG in Sustainability
- Vol. 12 (17) , 7104
Open AccessThe Church Tower of Santiago Apóstol in Montilla: An Eco-Sustainable Rehabilitation Proposal
Is it possible to carry out eco-sustainable rehabilitations on specially protected buildings? This is the main question and starting point for this research. We will use the tower of the Church of “Santiago Apóstol” in Montilla as a case study; with its most remote antecedents in the 15th century, it is an emblematic building of one of the most important cities in the Cordovan countryside and is listed as an Asset of Cultural Interest (Bien de Interés Cultural or BIC) as of 2001. The application of eco-efficiency criteria in the rehabilitation of this type of building might stimulate the reactivation of the construction sector in the rural area, positively impacting the promotion of a circular economy. To this end, a general methodology has been established for carrying out eco-sustainable renovations on this type of building, which defines indicators for evaluating the eco-sustainability of such interventions. This methodology is applied to the case study of this important building in Montilla to ensure that a feasible intervention has been proposed, aligned with three basic pillars of sustainability that considers its environmental, economic, and social impact.
- Open Access
- 7 March 2019
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 8 (3) , 132
Combining Object-Based Image Analysis with Topographic Data for Landform Mapping: A Case Study in the Semi-Arid Chaco Ecosystem, Argentina
This paper presents an object-based approach to mapping a set of landforms located in the fluvio-eolian plain of Rio Dulce and alluvial plain of Rio Salado (Dry Chaco, Argentina), with two Landsat 8 images collected in summer and winter combined with topographic data. The research was conducted in two stages. The first stage focused on basic-spectral landform classifications where both pixel- and object-based image analyses were tested with five classification algorithms: Mahalanobis Distance (MD), Spectral Angle Mapper (SAM), Maximum Likelihood (ML), Support Vector Machine (SVM) and Decision Tree (DT). The results obtained indicate that object-based analyses clearly outperform pixel-based classifications, with an increase in accuracy of up to 35%. The second stage focused on advanced object-based derived variables with topographic ancillary data classifications. The combinations of variables were tested in order to obtain the most accurate map of landforms based on the most successful classifiers identified in the previous stage (ML, SVM and DT). The results indicate that DT is the most accurate classifier, exhibiting the highest overall accuracies with values greater than 72% in both the winter and summer images. Future work could combine both, the most appropriate methodologies and combinations of variables obtained in this study, with physico-chemical variables sampled to improve the classification of landforms and even of types of soil.
- 7 March 2019
- Published by MDPI AG in ISPRS International Journal of Geo-Information
- Vol. 8 (3) , 132
Open AccessCombining Object-Based Image Analysis with Topographic Data for Landform Mapping: A Case Study in the Semi-Arid Chaco Ecosystem, Argentina
This paper presents an object-based approach to mapping a set of landforms located in the fluvio-eolian plain of Rio Dulce and alluvial plain of Rio Salado (Dry Chaco, Argentina), with two Landsat 8 images collected in summer and winter combined with topographic data. The research was conducted in two stages. The first stage focused on basic-spectral landform classifications where both pixel- and object-based image analyses were tested with five classification algorithms: Mahalanobis Distance (MD), Spectral Angle Mapper (SAM), Maximum Likelihood (ML), Support Vector Machine (SVM) and Decision Tree (DT). The results obtained indicate that object-based analyses clearly outperform pixel-based classifications, with an increase in accuracy of up to 35%. The second stage focused on advanced object-based derived variables with topographic ancillary data classifications. The combinations of variables were tested in order to obtain the most accurate map of landforms based on the most successful classifiers identified in the previous stage (ML, SVM and DT). The results indicate that DT is the most accurate classifier, exhibiting the highest overall accuracies with values greater than 72% in both the winter and summer images. Future work could combine both, the most appropriate methodologies and combinations of variables obtained in this study, with physico-chemical variables sampled to improve the classification of landforms and even of types of soil.
- Open Access
Assessment of the Persistence of Avena sterilis L. Patches in Wheat Fields for Site-Specific Sustainable Management
This paper aims to evaluate the spatial persistence of wild oat patches in four wheat fields over time to determine the economic feasibility of using late-season wild oat maps for early site-specific weed management (SSWM) next season. The spatial persistence of wild oat patches was analyzed by three tests: land use change detection between years, spatial autocorrelation, and analysis of spreading distance. The temporal trend of wild oat patch distribution showed a clear persistence and a generalized increase in the infested area, with a noticeable level of weed aggregation and a tendency in the new weed patches to emerge close to older ones. To economically evaluate the SSWM, five simulations in four agronomic scenarios, varying wheat yields and losses due to wild oat, were conducted. When yield losses due to wild oat were minimal and for any of the expected wheat yields, some SSWM simulations were more economically profitable than the overall application in most of the fields. Nevertheless, when the yield losses due to wild oat were maximal, all SSWM simulations were less profitable than overall treatment in all the analyzed fields. Although the economic profit variations achieved with SSWM treatments were modest, any of the site-specific treatments tested are preferred to herbicide broadcast over the entire field, in order to reduce herbicide and environmental pollution.
Open AccessAssessment of the Persistence of Avena sterilis L. Patches in Wheat Fields for Site-Specific Sustainable Management
This paper aims to evaluate the spatial persistence of wild oat patches in four wheat fields over time to determine the economic feasibility of using late-season wild oat maps for early site-specific weed management (SSWM) next season. The spatial persistence of wild oat patches was analyzed by three tests: land use change detection between years, spatial autocorrelation, and analysis of spreading distance. The temporal trend of wild oat patch distribution showed a clear persistence and a generalized increase in the infested area, with a noticeable level of weed aggregation and a tendency in the new weed patches to emerge close to older ones. To economically evaluate the SSWM, five simulations in four agronomic scenarios, varying wheat yields and losses due to wild oat, were conducted. When yield losses due to wild oat were minimal and for any of the expected wheat yields, some SSWM simulations were more economically profitable than the overall application in most of the fields. Nevertheless, when the yield losses due to wild oat were maximal, all SSWM simulations were less profitable than overall treatment in all the analyzed fields. Although the economic profit variations achieved with SSWM treatments were modest, any of the site-specific treatments tested are preferred to herbicide broadcast over the entire field, in order to reduce herbicide and environmental pollution.