AGRO AI: A compact solution for modernizing the agriculture using NASA’s satellite data and artificial intelligence

This paper presents the results of a systematic literature review of climate change adaptation and resilience in coastal agriculture in Bangladesh. It explores the existing adaptation measures against climatic stresses. It investigates the extent of resilience-building by the use of these adaptation measures and identifies major challenges that hinder the adaptation process within the country. The review was conducted by following the systematic methods of the protocol of Preferred Items for Systematic Review Recommendations (PRISMA) to comprehensively synthesize, evaluate and track scientific literature on climate-resilient agriculture in coastal Bangladesh. It considered peer-reviewed English language articles from the databases Scopus, Web of Science and Science Direct between the years 2000 and 2018. A total of 54 articles were selected following the four major steps of a systematic review, i.e., identification, screening, eligibility and inclusion. Adaptation measures identified in the review were grouped into different themes: Agricultural adaptation, alternative livelihoods, infrastructure development, technological advancement, ecosystem management and policy development. The review revealed that within the adaptation and resilience literature for coastal Bangladesh, maladaptation, gender imbalance and the notable absence of studies of island communities were gaps that require future research.

In the face of growing challenges in agriculture due to pests and diseases, the need for advanced monitoring and forecasting techniques has become increasingly critical.Climate change, global trade, and the adaptation of pests to traditional control methods have further complicated this landscape. This Research Topic offers a collection of studies highlighting the latest advancements in pest and disease monitoring, focusing on the development and application of innovative algorithms, technologies, and practical solutions to mitigate the impact of these threats on agriculture.Recent advances in deep learning, such as fast Fourier Convolutional Networks, have shown promise in distinguishing between similar symptoms like wheat yellow rust and nitrogen deficiency using Sentinel-2 time series data (Shi et al., 2023). These techniques underscore the power of modern AI to refine diagnostic accuracy, which is crucial for early intervention and targeted management. Similarly, the spatial ensemble model has been employed to assess the potential risk zones of Pierce's disease across Europe, integrating multiple data sources to offer more reliable predictions for pest management (Yoon et al., 2023).Within controlled environments, greenhouse-based pest monitoring has seen significant improvements due to the implementation of deep learning and machine vision (Zhang et al., 2023). Automatic identification systems are now capable of realtime recognition of pests, thanks to the deployment of sophisticated neural networks.The integration of UAV technology with deep learning also extends pest monitoring capabilities to broader agricultural landscapes. For instance, studies on Brandt's vole detection and counting via UAV-based systems exemplify the ability to efficiently monitor field conditions (Wu et al., 2024), while multispectral imaging from UAVs provides detailed nutritional assessments, such as potassium levels in potato plants (Ma et al., 2023).Machine learning architectures have also been developed to handle complex diagnostic tasks in challenging environments (Liu Y. et al., 2024). Techniques like the multi-scale double-branch GAN-ResNet for rice pest identification demonstrate the application of advanced algorithms in complex scenarios, including those with variable backgrounds (Hu et al., 2023). Other lightweight deep learning models, such as MS-Net, are designed to be both accurate and efficient, focusing on optimizing computational resources without compromising precision (Quan et al., 2023).The fusion of multispectral and hyperspectral data has shown great potential in early disease detection across different crop types and ecosystems. The MSGF-GLP method, for example, utilizes visible and hyperspectral data to identify stressed vegetation, enhancing early detection capabilities (Zhou et al., 2023). These approaches highlight the increasing role of spectral data in disease management, offering more nuanced insights into plant health (Huang et al., 2023).Field-based applications of these technologies have also made considerable strides. Studies on the penetration of fog droplets in fruit tree canopies (Sun et al., 2024) reveal the multifactorial elements affecting pesticide delivery efficiency. These findings are crucial for improving precision agriculture, allowing targeted interventions that minimize pesticide use while maximizing coverage. Lightweight models like the enhanced CNN (Dai et al., 2023) for pepper leaf disease recognition showcase how AI can be applied to specific crops, even in complex agricultural settings. Similarly, research on weed identification in soybean fields using lightweight segmentation models such as DCSAnet demonstrates (Yu et al., 2023) the application of optimized AI architectures in practical field conditions.The rise of mobile applications powered by AI, such as GranoScan (Dainelli et al., 2024) for in-field wheat threat identification, reflects the growing trend of democratizing technology for farmers. These tools provide accessible and accurate diagnostic capabilities, empowering agricultural stakeholders with real-time data.Likewise, the development of UAV spraying systems (Liu Y. et al., 2024) that account for pest activity patterns, such as thrips during the cotton flowering period, illustrates the synergy between automated technologies and pest behavior research. Additionally, a risk-based regionalization approach has been proposed for the area-wide management of HLB vectors in the Mediterranean Basin (Galvan et al., 2023), offering a strategic perspective to mitigate the spread of disease.The Research Topic also addresses challenges associated with AI applications in pest monitoring. Issues such as complex environments, small object detection, and the variability of natural conditions continue to test the limits of current technologies.Innovations like the Skip DETR model (Liu B. et al., 2023), which integrates skip connections for small object detection, and the adaptive filtering fusion method for pest recognition, indicate ongoing efforts to overcome these obstacles (Chen et al., 2023).In summary, this Research Topic offers a comprehensive overview of current innovations in pest and disease monitoring. The articles included emphasize the growing role of AI, machine learning, and advanced imaging technologies in modern agriculture. Together, these studies not only demonstrate the effectiveness of cuttingedge solutions but also underline the importance of continued collaboration across disciplines to address the evolving challenges in pest and disease management.

The most important factor to take into account when building solar energy systems is solar irradiation. It is impossible to measure sun irradiation everywhere due to its high cost and difficulties. Additionally, in some places, the GHI was overpredicted by 25% by NASA satellite data. The main goal of this study was to develop an artificial neural network (ANN) model that can reduce the error in satellite data by predicting global horizontal irradiation (GHI) using inputs from satellite data obtained from the NASA Power Data viewer. The MAPE in the satellite was decreased by 35.8% in Peshawar, 10.2% in Islamabad, and 8.9% in Multan using the ANN models. Additionally, the results showed that all ANN models' predictions were more precise than satellite data.

Abstract. The latest generation of geostationary satellites provide Earth observations similar to widely used polar-orbiting sensors but at intervals as frequently as every 5–10 min, making them ideal for studying the diurnal dynamics of land–atmosphere interactions. The NASA Earth Exchange (NEX) group created the GeoNEX datasets by collating data from several geostationary platforms, including GOES-16/17/18, Himawari-8/9, and GK-2A, and placing them on a common grid to facilitate use by the Earth science community. Here, we document the GeoNEX Coincident Ground Observations (GeCGO) dataset for terrestrial ecosystem studies and provide examples for its use. Currently, GeCGO provides GOES-16 Advanced Baseline Imager (ABI) data over a 10 km × 10 km area surrounding 1586 network sites across the Americas. GeCGO makes it easy to compare the time series of geostationary data with the diurnal ground observations, including carbon/water fluxes and aerosol optical depth, and is extensible to other regions. We also develop GeoNEXTools to facilitate analyses that require both GeoNEX data and other NASA satellite data. The objectives of this paper are to introduce GeCGO and GeoNEXTools and demonstrate their applications. First, we describe the details of GeCGO and GeoNEXTools. Second, we explain how GeCGO can be integrated with other satellite data. Finally, we showcase comparisons between GeCGO and observations from three ground-based networks. GeCGO is available at https://doi.org/10.25966/y5pe-xp41 (Hashimoto et al., 2025).

The semi-arid tropics being dominant region is primarily agrarian with rainfed traditional agricultural production systems. Jawhar is a tribal block in Maharashtra, India characterized by high rainfall, water scarcity, degraded soils and low crop productivity. ICRISAT in collaboration with JSW has initiated agricultural interventions with watershed approach. Over a two-year period, the project has demonstrated various activities to build the resilience against climate change to cope with varying climatic risks and to improve livelihoods. Conservation of available resources through various measures was carried out with active community participation. Agriculture is the main source of livelihood of the community. Soil health management, rainwater harvesting, soil conservation, promotion of improved cultivars, introduction of new crops (crop diversification), income-generating activities and promotion of agronomic practices were the major interventions carried out in the project villages. These have taken farmers towards the path of building resilience to cope with climatic risks.

Discussion of some results of the effects of ionospheric irregularities on NASA satellite tracking and data acquisition operations. Ionospheric scintillation fading produced by irregularities has been observed at 136 MHz (vhf), 400 MHz (uhf), 1550 MHz (L-band) and 1700 to 2200 MHz (S-band). Details of these observations are presented. Vhf scintillation effects are evident in both auroral and equatorial regions. Fading effects decrease with increasing radio frequency in the auroral region. The same frequency dependence for fading is not observed in the equatorial region. Although there is a seasonal and diurnal character to scintillation in the equatorial region, fading effects are usually more severe than in the auroral region for a given radio frequency. Space diversity measurements indicate that reasonable solutions for vhf telemetry problems are available for either region. Space diversity should provide a solution for microwave frequencies as well. Ionospheric fading amplitude for 1700 MHz is relatively small in the auroral region. In the equatorial region amplitude fading levels for 1550-MHz signals from ATS-5 are often much larger than expected. Observations of the Apollo Lunar Surface Experiment Package (ALSEP) operating at 2300 MHz observed near the geomagnetic equator show fading peaks in excess of 15 dB.

The book begins with an introduction to sustainable farming, addressing the pressing need for a farming revolution in response to environmental challenges. It highlights the crucial role of technology, including environmental engineering and machine learning, in transforming agriculture into a more efficient and eco-friendly domain. From soil health management and water resource optimization to renewable energy integration and waste recycling, this book delves deep into the principles of environmental engineering applied to agriculture. One of the most groundbreaking aspects of this book is its exploration of machine learning in agriculture. It provides a user-friendly introduction to AI and predictive analytics for non-experts while covering advanced applications such as disease and pest detection, precision farming, and climate adaptation strategies. The book also discusses image recognition for crop health monitoring and the challenges of implementing AI-driven solutions in the farming sector. Readers will find inspiring success stories showcasing real-world applications of machine learning in modern agriculture. Smart agricultural practices form another pillar of this book, providing an in-depth look at innovative solutions like IoT-based farming systems, automated irrigation, agricultural drones, blockchain for supply chain transparency, robotics, and smart sensors. These technologies are paving the way for a more efficient and data-driven approach to farming, ensuring sustainability while maximizing productivity. A critical aspect of sustainable farming is soil health and fertility management. This book explores sustainable enrichment techniques, bioengineering for soil restoration, AI-driven soil analysis, and best practices such as crop rotation and companion planting. It also warns against the risks of over-fertilization and eutrophication, emphasizing the importance of balance in soil nutrition. Climate-smart agriculture is another vital component, addressing strategies for climate change adaptation, greenhouse gas mitigation, drought-resilient crops, and water management in changing climates. The book highlights the role of AI in climate adaptation and presents policies and success stories from around the world, illustrating effective approaches to climate-resilient farming. Additionally, the book covers sustainable crop management, ethical livestock farming, advanced irrigation techniques, and the economic and social impacts of smart agriculture. It discusses how technology can empower farmers, reduce costs, and address global food security challenges, while also bridging the urban-rural divide through education and training. For those interested in the policy and global perspectives of sustainable farming, the book provides an overview of international initiatives, government incentives, legal and ethical considerations, and collaborations between private and public sectors. It offers case studies demonstrating policy-driven agricultural transformations and insights into the future of farming. The concluding chapter envisions the future of sustainable agriculture, exploring emerging technologies such as AI, IoT, robotics, and big data in farming. It emphasizes the importance of a circular economy in agriculture and highlights the challenges that must be overcome for widespread adoption. Finally, it inspires readers to contribute to a global movement for sustainable farming and food security. With a blend of scientific research, practical applications, and forward-thinking strategies, Sustainable Farming Revolution is an indispensable guide for those seeking to harness the power of environmental engineering, AI, and smart agricultural practices to build a more sustainable and resilient future.

Climate Resilient Agriculture (CRA) aims to adapt agricultural and dependent socio-economic systems to the risks posed by the ongoing climate change. This essentially involves the adoption of various climate-smart engagements in the practice of crop production, animal husbandry, forestry, and fishery systems. Coastal Bangladesh has a very high presence of agriculturists, and the landscape is highly vulnerable to the various adverse impacts of climate change. The key challenges faced by the region are unprecedented extreme climatic events (frequent cyclones, droughts), saltwater ingress, coastal erosion, etc. Evidence-based analysis of the interaction of climatic risks with landscape and its social economic scape is a sine qua non to the design, implementation, and integration of CRA interventions in the landscape. Driven by these considerations, we have explored the context of coastal agriculture in Bangladesh with the following research objectives- i) analyse the measures taken for climate resilience of agricultural systems and climate change adaptation of the communities in the climate-vulnerable coastal areas of Bangladesh, ii) identify and explore the barriers in the adaptation engagements by the local communities, iii) suggest measures for pushing the frontiers of climate change adaptation through policy measures to improve the effectiveness of CRA interventions in the coastal areas. In order to address the questions, this study followed a Rapid Assessment Process (RAP). It consisted essentially farmer’s interviews, focus group discussions and experts’ interviews. This was complemented by direct field observations as well. The results indicate that climate change adaptation pursued in the landscape can be grouped into a) planned adaptation and b) autonomous adaptation. It was found that the farmers had various autonomous adaptation measures and planned adaptation measures. Homestead gardening models and integrated farming models are found widely accepted autonomous adaptation engagements in the study area. Among many barriers, limited access to agricultural knowledge and technology adoption gaps limits the ability of farming communities to adapt their agricultural systems to climate change risks and impacts. The study recommends a strong case for providing policy and promotion coverage to the successful autonomous practices undertaken by the farming communities and to reduce to chances of maladaptation practices. Further, the validated adaptation measures need to be facilitated while actively scaling up the planned adaptation interventions to transform to climate-resilient agriculture.

Infection by the fungus Verticillium dahliae (Vd) and the bacterium Xylella fastidiosa (Xf) threatens the production of olives (Olea europaea L.) and almonds (Prunus dulcis Mill.) worldwide. Producing symptoms that resemble water stress or nutrient deficiency, infection by these vascular pathogens restricts water and nutrient flow through the xylem. Hyperspectral, narrow-band multispectral, and thermal imagery acquired at a high spatial resolution can detect disease symptoms, even before they are visible, potentially allowing growers to distinguish infected plants from those affected by confounding environmental stresses. Nevertheless, operational detection of vascular disease using high-resolution commercial satellite multispectral images remains to be evaluated. Here, we assessed the capacity of high-resolution Worldview-2 and -3 multispectral imagery to detect Xf and Vd infections in olive and almond orchards in Spain, Italy, and Australia between 2011 and 2021. We compared the accuracy of detecting both pathogens using the satellite imagery with results obtained using aerial high-resolution hyperspectral and thermal imaging, with model-inverted plant traits, solar-induced chlorophyll fluorescence (SIF), and thermal data as a reference. Our results using spectral plant traits to examine disease progression at all stages showed that traits and their importance varied as a function of disease severity. Worldview-2 and -3 detected the disease incidence with overall accuracies ranging from 0.63 to 0.83 and kappa coefficients (κ) ranging from 0.29 to 0.68. Nevertheless, detecting the early stages of disease with multispectral satellite data yielded poorer results, with κ values of 0.22–0.45, compared with κ values of 0.3–0.69 obtained from hyperspectral data. Typical multispectral bandsets available from satellite sensors cannot measure important plant traits such as the blue index NPQI, xanthophyll proxy PRIn, SIF, and anthocyanin levels, thus explaining the poorer results obtained from multispectral satellite data for the early detection of vascular diseases. Adding a thermal-based crop water stress indicator to the satellite data improved the overall accuracies by 10–15% and increased κ by >0.2 units. This work shows that commercial multispectral high-spatial resolution imagery can be used to detect intermediate and advanced Xf and Vd infection, but that the early detection of disease symptoms requires hyperspectral and thermal data.

<p>The city of Rio de Janeiro is situated within a coastal region with steep slopes, intense seasonal rainfall, and vulnerable populations located on marginal slopes. Landslides are a seasonal challenge within the city and proximate regions and increasing real-time awareness of the hazard and exposure is paramount to saving lives and mitigating damage. A local alerting system has been developed for the city that leverages a global landslide hazard assessment for situational awareness (LHASA) framework, developed by NASA, with local rainfall thresholds and landslide susceptibility information. The LHASA-Rio system uses a decision tree approach to first identify extreme rainfall based on a series of rainfall thresholds established by Geo-Rio (the City’s agency responsible for landslide hazards) for 1 hour, 1 day or 1 hour and 4 day thresholds. This is then coupled with information on landslide susceptibility also developed by the Geo-Rio team. The LHASA-Rio system has been running operationally since 2017 within the city to provide real-time, high resolution estimates of areas within the city at higher hazard at 15-minute intervals consistent with the rainfall gauge network distributed throughout the city. Results of the LHASA-Rio system indicate excellent performance for several case studies where extreme rainfall triggered landslides within the city over areas identified as high hazard zones by LHASA-Rio. The model has recently been updated to accommodate additional rainfall thresholds to differentiate moderate to very high and critical intensities. The modeling effort is also incorporating information on landslide exposure by connecting the hazard estimates to city-wide data on population, road networks and other infrastructure. The goal of this system is ultimately to provide key tools to emergency response teams, civil protection and other hazard monitoring organizations within Rio’s City Government in real-time and provide  actionable information for key communities, city management and planning. Future work of this system is the application of a regional precipitation forecast to improve the lead time.</p><p>This work has been done in partnership through an agreement established between NASA and the City of Rio de Janeiro in 2015 that was recently extended in 2020. This agreement seeks to support innovative efforts to better understand, anticipate, and monitor hazards and environmental issues, including heavy rainfall and landslides, urban flooding, air quality and water quality in and around the city. This collaboration leverages the unique attributes of NASA's satellite data and modeling frameworks and Rio de Janeiro's management and monitoring capabilities to improve awareness of how the city of Rio may be impacted by hazards and affected by climate change. If the success of this technology is demonstrated, other cities in the world with physiographic and socioeconomic characteristics similar to Rio de Janeiro may benefit by implementing, or strengthening, their own Early Warning Systems for landslides triggered by heavy rains using LHASA's open source algorithms and the experience gathered by the use of LHASA-Rio. This presentation highlights the achievements and advancements of the LHASA-Rio system and discusses lessons learned regarding the applications of the landslide modeling systems to advance decision-relevant science at the city level.</p>

Since from the dawn of mankind, necessity gives birth to technology. PV is the most promising source of renewable energy in India. The need of PV technologies in the present day is unavoidably necessary, as these help the consumers to maintain sustainability, by providing innovative PV technology options and more subsidies by the government. This will help the future generations enjoy their right to clean environment and can consume energy as per their needs. Although the Renewable energy sources are accompanied with certain constraints as unreliability, unavailability and discontinuous generation; great deals of research works are being carried out on solar energy to produce electricity, which can suffice the disadvantages mentioned above. Solar PV technologies hold quite remarkable commitment for Bhubaneswar, India which has a high insolation of 4.5–5 kWh/m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> /day as per the data collected from Ministry of New and Renewable Energy, Government of India, for about 300 sunny days per year in India. Solar PV technologies are commercially feasible and produce technologically mature products which have existed in the country for many years. But still, the market share of solar energy fails to fulfil the expectations of the people [1]. Hence, keeping in mind the way a consumer thinks while buying a product, it can be said that if the solar products were a little less expensive along with the uninterrupted maintenance services offered by the companies, the willingness of people to go for the solar products would have been more [2]. Nevertheless, in rural areas, light is usually unavailable and if it does, the prime focus is given to incandescent light used for household lighting instead of fluorescent. System reliability, economy and environmental issues are major three issues for decentralised electrification. So, the need of the hour is to overcome these constraints by the implementation of RETScreen software. This software provides [2] the user with a broad range of options for assessing the technical, financial and environmental suitability for an investment in a 'clean energy' project. It integrates a number of databases to assist the site assessor, including a global database of climatic conditions obtained from 4,700 groundbased stations and NASA's satellite data [3].

Assessing the Economic Feasibility and Competitiveness Analysis of Photovoltaic Solar Power in the Colombian Caribbean based on NASA's Satellite Data

Reforestation with exotic species has often been used in arid and semiarid areas to restore degraded ecosystems. However, the effects of these plantations on soil biodiversity are still under debate. In the present study, we aimed to evaluate the long-term impacts (>60 years) of exotic plantations with Acacia cyclops and Pinus halepensis on soil biodiversity in an insular arid ecosystem of high ecological value. To do so, we study soil quality and soil arthropod communities in patches of vegetation under uniform edaphoclimatic conditions. Soil quality assessment was carried out by developing an ad-hoc Soil Quality Index (SQI) across seven sites, including two plantations ( Pinus or Acacia ), two degraded areas with a low cover of native species, and three sites with a high cover of native species. Whole organism community DNA (wocDNA) metabarcoding and barcoding were used to analyse key soil arthropod groups (Coleoptera, Acari and Collembola) recognized as habitat quality and biodiversity indicators. Our findings show that exotic plantations improved soil quality compared to degraded sites, with a considerable increase in the organic carbon pool, macronutrients and microbiological activity (SQI = 0.53 ± 0.12 vs. 0.29 ± 0.06). This improvement did not reach the values recorded in soils with a high cover of preserved native flora (SQI = 0.65 ± 0.12), with some exceptions. Richness of mesofauna and Coleoptera was lower in degraded areas (4.4 ± 1.6 and 0.4 ± 0.7, respectively) followed by exotic plantations (9.5 ± 2.6 and 1.2 ± 0.9) and permanent native vegetation (14.1 ± 5.5 and 2.2 ± 1.8). Soil quality significantly explained up to 52 % and 17 % of the variance in the richness of mesofauna and Coleoptera, respectively. While exotic plantations appear to prevent further land degradation in terms of soil quality, multivariate analysis shows that the structure of soil arthropod communities, particularly in Pinus plantations and to a lesser extent in Acacia plantations, differs significantly from that of soils in ecosystems with remnant native flora. These results highlight the need for a careful balance between biodiversity conservation and soil health management, especially in areas susceptible to desertification. • Soil fauna in exotic plantations is not as complex as in remnant native ecosystems. • Ad-hoc soil quality index correlates with richness of key invertebrate groups. • Exotic plantations create transitional states between native and degraded areas. • Introduced species incidence in exotic areas doubles that of native ecosystems.

Rising temperatures, unpredictable monsoon patterns, groundwater depletion, and a reduction in soil fertility are all signs of the ongoing climate stress that South Haryana, a semi-arid agro-ecological area, suffers. These issues put rural lives and agricultural output at risk, underscoring the need of switching to comprehensive and climate-resilient development strategies. This research looks at how the region's climate resilience is shaped by integrated agricultural systems, resource-conserving technology, diversity, water-efficient practices, and institutional support. Based on official files, statistical databases, secondary literature, and field observations, the study examines the ecological, socioeconomic, and technical aspects of South Haryana's agriculture. Crop diversification, micro-irrigation, agro-forestry, sustainable soil management, integrated nutrient application, and digital agriculture are all highlighted, along with the region's main weaknesses. The adoption behavior of farmers and the facilitating function of state policies, market connections, and extension services are given particular consideration. Results show that agricultural systems that go beyond crop-centric methods to include livestock, horticulture, natural resource management, and community-based adaptation mechanisms are more resilient to climate change. The study comes to the conclusion that, in South Haryana's climate-stressed agrarian terrain, holistic agricultural development provides a feasible route for environmental stability, sustainable rural expansion, and enhanced adaptive capability. . KEYWORDS :Holistic agricultural development, Climate-resilient farming, Sustainable agriculture, South Haryana, Climate adaptation, Integrated farming systems, Micro-irrigation, Crop diversification, Soil health management, Water-use efficiency, Agricultural sustainability, Farmer livelihoods, Climate vulnerability, Institutional support, Agricultural innovation

Simulation of water productivity of wheat in northwestern Bangladesh using multi-satellite data