3.1. Articles reviewed
In this research, a total of 39 articles were retrieved from the 423 articles searched using specified keywords (Table 3). A comprehensive article categorization strategy was implemented to systematically organize a varied set of studies centered around agricultural innovations. The categorization strategy was structured based on three key dimensions: the type of technology/technique utilized, the agricultural application area, and the purpose of innovation. Under the dimension of technology/technique, articles were classified under "Precision agriculture," encompassing innovations related to advanced farming methodologies and studies leveraging technologies and platforms.
Table 3
Agricultural innovations of the retrieved
| Innovation | Purpose | Source |
| 1 | Unmanned aerial sprayer | Aerial spray system for agricultural applications | Agurob et al. [15] |
| 2 | UAV-based multispectral vegetation monitors | Vegetation indices and leaf color chart observations | Bacsa et al. [5] |
| 3 | Laser-controlled land leveling | Laser-controlled land leveling in rice production | Nguyen-Van-Hung et al. [16] |
| 4 | Soil moisture sensor system | Wireless soil moisture sensor for precision agriculture | Cruz et al. [4] |
| 5 | Drone-based GIS Mapping | Drone-based GIS Mapping of Cassava Pythoplasma Disease | Plata et al. [17] |
| 6 | Wireless sensor technology and GPS | Low-cost, portable IoT dashboard for smart farming. | Santos et al. [18] |
| 7 | Integrated rice-duck farming | Ducks feed on pests, and weeds, and fertilize rice. | Baldo & Laureta, [19] |
| 8 | SCoPSA as a sustainable and viable farming method | SCoPSA, contour farming, hedgerows, double-row planting, agro-waste utilization | Sabado et al. [20] |
| 9 | Alternate wetting and drying technology | AWD technology improves Agusan soil rice cultivation | Magahud et al. [21] |
| 10 | Indigenous knowledge systems and practices for managing natural environments | Natural environment management, soil erosion control, and productivity approaches. | Gomez Jr. [22] |
| 11 | Conversion of rice husks into biochar | Biochar, RHB soil amendment, nano silica synthesis. | Sarong et al. [23] |
| 12 | Development of SAKAHANDA | SAKAHANDA: Android app for farmers and Municipal Agriculture Office | Batoon et al. [24] |
| 13 | Linear programming for cost minimization of feeds | Linear programming minimizes feed costs | Borlas et al. [25] |
| 14 | Smart greenhouse system | Smart greenhouse: Arduino control, GSM, SMS notifications for environment management | Elenzano, [26] |
| 15 | Vertical Farming using Hydroponic Technology | Hydroponics for onion, focus on acceptability and viability. | Pascual et al. [27] |
| 16 | IoT-enabled systems and multiple regression | IoT, regression predict frost in highland crops | Mendez & Dasig, [28] |
| 17 | Infrared thermography for grading rough rice | Precision agriculture: ICT, infrared thermography, Smart Sensor AR991 | Bejarin & Fajardo, [29] |
| 18 | Local unmanned aerial vehicle (UAV) pesticide sprayer | UAV pesticide sprayer for rice fields | De Padua et al. [6] |
| 19 | Soil sensors via a Wireless Sensor Network | IoT system links environmental, soil sensors via WSN | Lorilla & Cabaluna et al. [30] |
| 20 | Wireless water level sensors | Wireless water level sensors for AWD irrigation management | Pereira et al. [31] |
| 21 | Nano fertilizer called FertiGroe | Nano fertilizer called FertiGroe for banana | Augustus & Domingo [32] |
| 22 | Vision-based velocity estimation combined | For accurate spot spraying without auxiliary velocity measurement | Sanchez & Zhang, [33] |
| 23 | Support Vector Machine classifier and CIELab color space | For automatic tomato ripeness identification | Garcia et al. [34] |
| 24 | GPS, sensors, and data analytics to optimize agricultural practices | GPS, sensors, and data analytics to optimize lettuce production | Lauguico et al. [7] |
| 25 | Aerial vision-based proximal sensing with a low-altitude UAV | To estimate weed and pest damage in eggplant | de Ocampo and Dadios, [35] |
| 26 | Artificial bee colony-optimized visible oblique dipyramid greenness index | For accurate estimation of lettuce crop parameters using images | Concepcion II et al. [36] |
| 27 | Computer application for identifying and determining mango pests | Iidentifying and determining mango pests using images | Rocha IV and Lagarteja, [37] |
| 28 | Automatic identification for Abaca Bunchy Top Disease | Automatic identification for Abaca Bunchy Top Disease | Patayon & Crisostomo, [38] |
| 29 | Potassium nanofertilizer using kappa-carrageenan | Potassium nanofertilizer using kappa-carrageenan as a carrier | Toledo et al. [39] |
| 30 | Integration of sensor applications, data analysis, and cloud-based data centers | IoT technology for automated estrus detection | Arago et al. [3] |
| 31 | IoT and Machine Learning for monitoring plants | Monitoring coffee plants nutritional deficiencies | Espineli and Lewis, [1] |
| 32 | Multi-temporal Synthetic Aperture Radar TerraSAR-X and Sentinel-1 | Rice area mapping and determine the Start of Season (SoS) | Gutierrez et al. [40] |
| 33 | Weather-Rice-Nutrient Integrated Decision Support System (WeRise). | Accuracy of the Weather-Rice-Nutrient Integrated Decision Support System | Hayashi et al. [41] |
| 34 | Deficit irrigation as a water-saving management strategy | water-saving management strategy for corn production | Painagan & Ella, [42] |
| 35 | Wireless sensor technology and GPS | Low-cost, portable cloud-based smart farming system | Santos et al. [18] |
| 36 | Arduino-based automated data acquisition system | Automated data acquisition system for hydroponic farming | Tagle et al. [2] |
| 37 | Agrinex, a low-cost wireless mesh-based smart irrigation | Low-cost wireless mesh-based smart irrigation | Tiglao et al. [43] |
| 38 | GIS-based land suitability model | Model for selecting agricultural tractors in lowland rice ecology | Amongo et al. [44] |
| 39 | Prototype design of a smart irrigation system using Internet of Things (IoT) | Internet of Things (IoT) for monitoring a vegetable farm | Velasco, [8] |
The agricultural application area dimension facilitated the grouping of articles into categories like "Sustainable farming practices," highlighting innovations contributing to environmentally conscious and sustainable farming methods. Other categories included "Novel materials/equipment," focusing on studies introducing new materials or equipment in agriculture, and "Image analysis," which emphasized innovations utilizing image processing techniques. Lastly, the purpose of the innovation dimension featured the "Decision support systems" category, specifically targeting innovations geared towards enhancing analytics, monitoring, and decision-making processes in farming. This structured categorization approach allowed for a comprehensive understanding of the various facets of agricultural innovations addressed in the retrieved articles.
Distribution of agricultural innovation categories in reviewed articles
The reviewed articles (n = 39) on agricultural innovations in the Philippines were categorized into five broad domains: precision technology, sustainable farming practices, novel materials/equipment, image analysis, and decision support systems (Fig. 2). Image analysis claimed the largest share, constituting 26.00% of articles, and involved innovations utilizing imaging techniques and analytics for crop monitoring and disease detection. This emphasis on image analysis highlights the significance of advanced cameras, sensors, and AI-enabled image recognition as emerging technologies suitable for Philippine agriculture. Sustainable farming practices followed with the next highest share at 23.00%, underscoring the prominence of techniques like conservation agriculture and integrated pest management for enhancing environmental sustainability. Together, technology-driven analytical innovations and sustainable agricultural practices comprised almost half of the identified innovations, indicating their high potential for shaping the future of Philippine agriculture, as reflected in the reviewed literature. The remaining half included decision support systems (21.00%), precision technology (15.00% of articles), and novel materials/equipment (15.00%). This distribution highlights emphases on cutting-edge technological innovations utilizing imagery, sensors, and computing, as well as sustainable practices for reduced environmental impact. Image analysis, as one of the significant A.I. tools in agricultural innovation [45], employs image processing, machine learning, and deep learning for disease identification in crops, such as weed detection in wheat crops. Hyperspectral image analysis is also utilized for crop yield and biomass estimation [46], demonstrating the numerous technological applications within the agricultural innovation landscape. Additionally, research underscores the essential role of sustainable agricultural innovation in enhancing the sustainable agricultural value chain and promoting a systematic overhaul in the agriculture sector [47]. Agricultural innovation is considered a crucial aspect of the global shift toward more sustainable and robust farming systems [48]. Initiatives like responsible agricultural mechanization innovation and the development of gender-specific programming [49, 50] further contribute to this transformative agenda. Collectively, these mixed approaches and initiatives indicate that agricultural innovation efforts in the Philippines span a broad range of complementary strategies, reflecting the multifaceted nature of advancements in the sector.
Distribution of agricultural innovation across crop and animal types
Figure 3 illustrates the distribution of agricultural innovations across various crop and animal types as examined in the articles. Rice holds the foremost position, with innovations addressing lowland, upland, and traditional rice farming, constituting 33.33% of the total. This substantial emphasis on rice is unsurprising, given its status as a staple crop and the principal agricultural product in the Philippines. The imperative for yield improvements amid land constraints and climate threats propels significant research interest in rice. Following closely are vegetables at 17.94%, underscoring the critical importance of horticultural efficiency due to the escalating demand for vegetables. In contrast, innovations for other key crops like banana, coffee, and mango have notably low shares, pointing to existing research gaps for these crops. Livestock innovations contribute 7.69%, despite the evident growth potential in the meat industry, signaling the necessity for additional studies on the substantial fisheries and poultry sectors. While the majority of Filipinos derive their livelihoods from farms, only 7.69% of innovations target upland sectors, revealing an imbalanced representation across commodities. Additionally, 20.51% of studies did not specify any crop, making geographical extrapolation challenging. This lack of specificity in a significant portion of studies complicates the geographical interpretation of findings. The absence of clear crop identification raises questions about the generalizability of results to specific agricultural contexts. Collectively, these pieces of information highlight a disproportionate focus on rice compared to other equally vital agricultural commodities in the Philippines. This emphasizes the urgency for diversification of research efforts, with a call for more innovations directed at high-value crops, livestock/poultry, coconut, and upland farmers to foster balanced and inclusive growth.
Geographic representation of agricultural innovation in the Philippines
Figure 4 presents the geographical distribution of agricultural innovations examined in the reviewed articles. A significant majority of innovations, totaling 69.23%, are concentrated on Luzon, particularly in central and northern areas. This geographical skew is expected, considering Luzon's status as the country's rice bowl and economic center. The fertile land and suitable climate in northern Luzon make it an ideal region for rice cultivation. The northern part of Luzon contributes significantly to the Philippines' rice production, playing a crucial role in the local economy. However, there is a notable dearth of studies focusing on the central and southern islands of Visayas (2.56%) and Mindanao (10.25%), which are major agricultural hubs renowned for their exports of tropical fruits, vegetables, and seafood. Additionally, 17.94% of articles do not specify the geographical context, impeding the localization of findings. This indicates a substantial fragmentation in research efforts, with insufficient
emphasis on key farming regions beyond Luzon. As the Philippines aims for food security and agricultural competitiveness, growth opportunities exist in the fertile lands and coasts of Visayas and Mindanao. The potential of these regions is highlighted by their status as major agricultural hubs. Visayas and Mindanao are well-known for their agricultural exports, emphasizing the need for a more balanced representation in research efforts. Achieving comprehensive development in the sector requires addressing the unique challenges, traditional practices, terrain suitability, and local farmer needs in these regions. To tap into the potential of smallholder tribal communities dependent on agri-livelihoods in remote southern areas, unified nationwide strategies for innovation transfer and capacity building should accompany studies for a more extensive impact. This approach ensures a holistic and inclusive development of the agricultural sector across various crops, technologies, and geographies, aligning with the broader goals of the Philippines in agriculture.
Key implementers
Table 4 highlights the key contributors to agricultural innovations in the examined articles. The University of the Philippines Los Baños stands out with a notable 12.8% share, emphasizing the pivotal role of academic research in advancing the agricultural sector. This significant contribution underscores the university's commitment to fostering innovation in agriculture. Numerous universities across Luzon are actively involved in innovating for regional farming needs, primarily concentrated in and around Metro Manila. Notably, research institutes like IRRI and the Philippine Rice Research Institute focus specifically on issues within the rice sector.
Table 4
Key implementers of agricultural innovations in the Philippines
| Key implementers | N = 39 | Percentage |
| AMA University Quezon City, Philippines | 2 | 5.1 |
| Batangas State University, Batangas | 1 | 2.5 |
| Benguet State University, Philippines | 1 | 2.5 |
| Bulacan State University | 1 | 2.5 |
| Central Luzon State University, Nueva Ecija, Philippines | 1 | 2.5 |
| De La Salle University, Manila, Philippines | 3 | 7.6 |
| Department of Agriculture Regional Field Office No. 02, | 1 | 2.5 |
| Far Eastern University Manila, Philippines | 1 | 2.5 |
| International Rice Research Institute (IRRI), Laguna | 2 | 5.1 |
| Isabela State University, Isabela | 4 | 10.2 |
| Japan International Research Center for Agricultural Sciences | 1 | 2.5 |
| Jose Rizal Memorial State University, Zamboanga del Norte | 1 | 2.5 |
| LORMA Colleges, San Fernando, La Union | 1 | 2.5 |
| Mapua University, Manila, Philippines | 1 | 2.5 |
| Mindanao State University – Iligan Institute of Technology | 1 | 2.5 |
| Nueva Ecija University of Science and Technology, Cabanatuan, Philippines | 1 | 2.5 |
| Partido State University, Camarines Sur, Philippines | 1 | 2.5 |
| Philippine Rice Research Institute, Agusan del Norte, Philippines | 1 | 2.5 |
| Samar State University, Catbalogan City, Philippines | 1 | 2.5 |
| Tarlac Agricultural University, Philippines | 1 | 2.5 |
| Technological Institute of the Philippines – Quezon City | 1 | 2.5 |
| Technological University of the Philippines, Manila, PHILIPPINES | 1 | 2.5 |
| University of Science and Technology of Southern Philippines | 1 | 2.5 |
| University of Southern Mindanao, Kabacan | 1 | 2.5 |
| University of the Philippines Diliman | 2 | 5.1 |
| University of the Philippines Los Baños, Laguna, Philippines | 5 | 12.8 |
| Visayas State University, Leyte | 1 | 2.5 |
However, there is a striking lack of studies originating from universities in Visayas and Mindanao, reiterating the geographical fragmentation observed earlier. This gap highlights the need for increased research efforts in these regions to ensure a more inclusive representation in agricultural innovations. Additionally, individual shares of contributors are relatively small, with most ranging from 2.5–5% only. The distribution of contributions among institutions reveals a pattern of modest individual shares. Most contributors are making contributions within the 2.5–5% range, indicating a lack of dominant players in the field. This distribution showcases the disjointed efforts plaguing the agricultural innovation landscape. Insufficient cross-institutional partnerships, fragmented solutions, and a lack of coordination hinder large-scale development or adoption after initial pilots. To foster more impactful and coordinated development in agricultural innovation, addressing the challenges of limited partnerships and fragmented solutions is crucial. A collaborative and coordinated approach involving institutions across different regions is imperative for the widespread adoption and success of agricultural innovations in the Philippines. For genuine sectoral impact, the unification of innovation ecosystems is critical, facilitated through Industry-Academia partnerships, technology transfer conduits, and nationwide farming extension services. Such unification ensures a more comprehensive and integrated approach to agricultural innovation. Collaborative efforts between academia and industry, coupled with effective technology transfer mechanisms, enhance the overall impact of agricultural innovations. Prioritizing applied research that addresses grassroots-level needs over theoretical studies is crucial for the practical implementation of innovative solutions. Most importantly, capacity building of end beneficiaries, namely small and marginal farmers, through financial, infrastructure, and skill development is crucial for them to effectively utilize innovative solutions, as currently sparse adoption levels indicate unpreparedness. Hence, consolidated, farmer-centric strategies are vital to shaping agricultural innovations into truly meaningful and widespread change agents.
Precision agriculture
Precision agriculture includes farming management concepts that leverage technological tools to enhance agricultural productivity and efficiency [4]. Emerging technologies, such as sensors, robots, drones, satellite imagery, and information technology, empower farmers to improve decision-making in crop production [18]. Precision agriculture practices include variable rate technology, automated equipment guidance systems, remote sensing, and specialized information management tools [5]. Effectively implemented precision agriculture enables farmers to use inputs more efficiently, reduce environmental impact, increase productivity, and boost profitability [16]. Recent literature on precision agriculture technologies and practices in the Philippines showcases innovative applications across various crop production systems. Plata et al. [17] developed a drone-based mapping system using geospatial data analysis to detect cassava diseases, illustrating the practical application of precision agriculture technologies in disease detection. Cruz et al. [4] designed a wireless sensor network that monitors soil moisture content to aid water management, serving as a tangible solution for precise water management and demonstrating the potential impact of precision agriculture in optimizing resource use. Bacsa et al. [5] utilized multispectral data from drones to assess crop nutrient status and guide fertilizer application, showcasing how precision agriculture can enhance sustainability through targeted and efficient input management based on real-time monitoring of crop growth conditions. However, barriers such as high upfront costs, lack of technical knowledge, challenges in data analysis, and absence of policy incentives can hinder the widespread adoption of precision agriculture [15]. This statement identifies key obstacles that impede the broad implementation of precision agriculture, emphasizing the importance of addressing these challenges to facilitate the adoption of precision agriculture practices [15]. Overcoming these barriers is crucial to unlocking the full potential of precision agriculture in the Philippines. More research and field testing are needed to validate benefits and support integration into existing production systems across diverse contexts in the Philippines [16]. As precision agriculture solutions become more accessible and tailored to local conditions, they can play a vital role in improving the productivity and resilience of Philippine agriculture amid climate change impacts and resource constraints. This statement emphasizes the potential transformative impact of precision agriculture in the context of Philippine agriculture, highlighting the crucial adaptation of precision agriculture solutions to local conditions for their effectiveness in addressing specific challenges faced by Filipino farmers. The integration of precision agriculture can contribute significantly to enhancing overall agricultural productivity and resilience in the Philippines as precision agriculture solutions continue to evolve and become more accessible, shaping the future of Philippine agriculture in an increasingly pivotal manner.
Sustainable farming practices
The reviewed studies highlight sustainable farming practices that enhance crop productivity while preserving environmental resources. Integrated rice-duck farming (IRDF), exemplifying this approach, allows ducks to feed on pests and weeds, fertilizing plants and increasing rice productivity [19]. Likewise, contour farming, hedgerow planting, and the sustainable corn production in sloping areas (SCoPSA) framework reduce soil erosion by 63% and enhance corn yield by 70% [21]. Additionally, alternate wetting and drying (AWD) technology for rice cultivation improves soil properties and plant growth compared to continuous flooding [20]. Agricultural waste products, such as rice husk biochar, enhance soil nutrients and plant biomass in degraded upland soil [23]. Vertical hydroponic farming of onions using rice husk substrates results in significantly higher bulb growth compared to field cultivation [27]. Innovations like nanosilica and mushroom compost derived from rice husks offer additional income streams for farmers [23, 20], showcasing the versatile use of agricultural waste products for sustainable practices and income generation. Moreover, studies emphasize technology's role in sustainable agriculture through precision monitoring and control of growing environments [26, 24] and optimizing productivity and costs [25]. Scaling out these innovations necessitates technical support and initial investment subsidies, with governments and organizations playing a pivotal role in facilitating adoption by smallholder farmers [27, 19]). The literature review demonstrates that sustainable intensification of smallholder farming is attainable through integrated pest management, efficient water and nutrient cycling practices, waste valorization, and precision agriculture technologies. Further research should concentrate on adapting these farming solutions to local biophysical and socioeconomic contexts across multiple agricultural systems and agroecological regions.
Novel materials/equipment
Recent agricultural innovations in the Philippines concentrate on the development of novel materials and equipment aimed at enhancing crop management practices. Notable innovations encompass IoT-enabled systems, infrared thermography technologies, unmanned aerial vehicles, wireless sensor networks, nano fertilizers, and water level sensors. For instance, Mendez and Dasig [28] employed IoT systems connected to sensors to monitor microclimate conditions, predict frost events, and automate irrigation scheduling. Their highland crop management system utilized multiple regression models for forecasting frost risk, transmitting real-time sensor data to a web platform, and delivering SMS alerts to farmers about predicted frost events. Bejarin and Fajardo [29] demonstrated the emerging application of infrared thermography for detecting moisture content and impurities in rough rice samples with high accuracy compared to standard methods. Evaluating unmanned aerial vehicles (UAVs) for agricultural tasks, De Padua et al. [6] developed an automated hexacopter UAV for aerial pesticide application over rice paddies, showcasing efficiency at a favorable unit cost. Lorilla and Cabaluna et al. 30] highlighted the emergence of wireless sensor networks coupled with IoT for real-time soil and irrigation monitoring in a smart irrigation system. Nano fertilizers, such as FertiGroTM tested by Augustus and Domingo [32] on banana plants, demonstrated significantly improved plant growth with the slow-release property making it suitable for direct soil application, potentially reducing fertilizer use and nutrient loss. Pereira et al. [31] contributed to the landscape by developing submersible water level sensors for measuring flood height in lowland rice fields, offering improved regulation of water usage in water-scarce regions and enhancing irrigation efficiency under alternate wetting and drying regimes.
Image analysis
Recent agricultural innovations in the Philippines increasingly integrate image analysis techniques for real-time and accurate crop monitoring and assessment. Machine vision and computer vision methods play a crucial role in achieving precision agriculture goals such as growth tracking, disease detection, yield forecasting, and selective treatment. An illustrative example is provided by Sanchez and Zhang [33], who developed a deep learning-based machine vision system to estimate the velocity of a precision sprayer system, showcasing the potential of image analysis for optimizing precision in agriculture practices. In pest management, Rocha and Lagarteja [37] employed convolutional neural networks (CNN) to automate the identification and classification of mango pests, achieving a high accuracy of 88.75%. Image analysis proves valuable in tracking crop growth parameters, as demonstrated by Garcia et al. [34], who applied support vector machines on RGB images to classify tomato ripeness, contributing to informed decision-making in agriculture. For monitoring plantation health, de Ocampo and Dadios [35] utilized aerial images to detect weeds and estimate pest damage in eggplant farms, achieving a 97.73% F1 score in isolating crops from the background. Concepcion et al. [36] introduced a novel greenness index computed from common smartphone images to estimate various lettuce crop parameters, providing non-invasive assessment capabilities for crop status. The success of these image analysis techniques stresses the potential of computer vision and machine learning methods for varying agricultural applications. Combining image analysis with IoT technology, as demonstrated by Arago et al. [3] in their smart dairy farming system, enables intelligent remote monitoring solutions. Further testing across various crop types, agricultural environments, and farm sizes, coupled with exploring more advanced neural networks and image processing algorithms, holds the potential to optimize accuracy and expand practical applications, as emphasized by Arago et al. [3] in their smart dairy farming system.
Decision support systems
Decision support systems (DSS) represent computer-based platforms integral to facilitating well-informed decision-making, particularly within agriculture. The components of agricultural DSS comprise sensors, IoT modules, satellite systems, analytical engines, crop simulation models, and user interfaces, utilizing diverse data sources related to weather, soil conditions, water availability, and crop growth stages. Algorithms, predictive models, and data visualization employed by DSS enable the provision of tailored advisories to farmers considering specific crop varieties, geography, soil health, and climatic factors. Studies on decision support systems in the Philippines emphasize their potential to enhance agricultural productivity and efficiency. The evaluation of the Weather-Rice-Nutrient Integrated Decision Support System (WeRise) by Hayashi et al. [41] exemplifies the integration of seasonal climate prediction and crop models to advise rainfed rice farmers on optimal sowing dates and varieties, resulting in higher grain yields compared to traditional practices. Gutierrez et al. [40] utilized multi-temporal SAR imagery and rule-based models to map rice areas and determine optimal planting windows, demonstrating strong correlations with farmer-reported planting dates. Sensor-based decision support systems, such as Tagle et al. [2] automated hydroponics monitoring and Tiglao et al. [43] smart irrigation prototypes, have showcased increased efficiency in resource use and crop yields. Prototypes like Velasco [8] solar-powered smart irrigation system and Santos et al. [18] cloud-based decision support dashboard further highlights potential improvements in agricultural productivity. These studies collectively illustrate the vital role advanced decision support systems, especially those incorporating ICT and precision agriculture techniques, play in optimizing resource utilization, increasing farmer incomes, and contributing to food security in the Philippines. The integration of wireless sensor data and GPS mapping by Santos et al. [18] is a concrete example enabling evidence-based planning for enhanced productivity and yield. The demonstrated success of these systems suggests their potential for widespread impact, emphasizing the need for further verification across multiple contexts and integration with emerging technologies to strengthen and expand the reach of these solutions.