Advances Remote Sensing Technique in Agriculture and Artificial Intelligence

Dear Colleagues,

Global agriculture faces multiple severe challenges, including population growth, climate change, resource scarcity, and food security concerns. In this context, achieving sustainable development, efficient resource utilization, and precise agricultural management has become a global priority. Remote sensing technology, as a core component of Earth observation systems, enables the macroscopic, dynamic, and objective acquisition of critical information—such as crop growth status, soil conditions, and field environments. The profound integration of remote sensing (RS) technologies and artificial intelligence (AI) is fundamentally reshaping the paradigm of precision agriculture, enabling unprecedented insights and decision-making capabilities for crop health monitoring, yield prediction, optimized resource allocation, and enhanced food security. High-resolution satellite, airborne, and UAV-based remote sensing continuously acquire multi-dimensional data—spanning spectral, thermal, and structural features—across agricultural landscapes. However, the emergence of massive volumes of heterogeneous data and their inherent complexity pose significant challenges to traditional analytical methods, simultaneously demanding more intelligent and highly efficient technological pathways.

This Special Issue aims to bring together cutting-edge research and applications that leverage AI/machine learning/deep learning methods to address complex challenges in agricultural remote sensing data processing, analysis, and interpretation. We welcome submissions that feature novel algorithms, innovative data fusion strategies, and practical applications that demonstrate significant advancements for precision agriculture.

Topics of interest include, but are not limited to, the following:

AI-powered crop type mapping and classification.

Deep learning for disease, pest, and weed detection/early warning systems.

Fusion of multi-source RS data using AI.

Predictive modeling for yield forecasting and water/nutrient stress.

Machine learning for agricultural Big Data processing and decision support.

Novel applications of RS and AI in livestock, forestry, or aquaculture.

Novel AI architectures tailored for agricultural remote sensing signals (e.g., hyperspectral, multispectral, LiDAR, SAR, thermal, and fluorescence). 

AI-enabled crop phenotype retrieval, stress detection, yield forecasting, and quality assessment. 

Climate-smart agriculture and carbon-sequestration monitoring via AI-enhanced remote sensing

1. Promote Algorithmic Innovation: Encourage the development of novel artificial intelligence models and architectures specifically designed to address key challenges in agriculture, such as limited training samples, multi-modal data fusion, temporal dynamics modeling, and model interpretability.
2. Expand Application Frontiers: Highlight how AI-driven approaches can enable transformative applications across spatial scales—from field-level monitoring to regional assessments—including crop phenomics, evaluation of agricultural ecosystem services, and intelligent agricultural supply chain systems.
3. Advance Technology Integration and Practical Validation: Emphasize the integration of AI with emerging sensing platforms such as unmanned aerial vehicles (UAVs), Internet of Things (IoT) devices, and agricultural robotics, while also promoting rigorous validation of models and their scalability across diverse agro-ecological environments.
4. Address Critical Challenges and Future Pathways: Provide a platform for in-depth discussion on persistent challenges in the field, including data accessibility and interoperability, model transparency, computational efficiency, and ethical considerations, while identifying promising directions for future research and implementation.

Novel AI Models and Methods:

Development and application of deep learning, transfer learning, meta-learning, few-shot learning, self-supervised learning, and reinforcement learning tailored to agricultural remote sensing challenges.

Intelligent fusion and collaborative inversion of multi-modal and multi-source remote sensing data, including optical, synthetic aperture radar (SAR), LiDAR, hyperspectral, and meteorological observations.

AI-driven spatio-temporal sequence modeling using advanced architectures such as Transformers, CNN-LSTM, and related hybrid models for crop growth monitoring and yield forecasting.

• Advanced Application Scenarios:
  
  • High-throughput crop phenotyping and genotype–phenotype association analysis enabled by AI and remote sensing.
  • Intelligent decision support systems for field-scale precision agriculture, including variable-rate fertilization, irrigation scheduling, and site-specific pesticide application.
  • Early detection and predictive modeling of pest and disease outbreaks using AI-enhanced remote sensing analytics.
  • Dynamic monitoring and quantitative assessment of abiotic stress impacts, including drought, flooding, soil salinity, and frost damage.
  • High-resolution mapping of farmland soil properties, such as moisture content, organic matter, and heavy metal contamination, through intelligent remote sensing interpretation.
  • Remote sensing-based estimation of agricultural carbon emissions and carbon sequestration potential using AI models.

• Key Supporting Technologies:
  
  • Development and domain adaptation of foundational and large-scale AI models specifically designed for agricultural remote sensing tasks.
  • Model interpretability, uncertainty quantification, and integration of physical mechanisms into data-driven AI frameworks.
  • Edge computing deployment and optimization of lightweight AI models on agricultural IoT sensors and unmanned aerial vehicles (UAVs).
  • Creation, curation, and open sharing of high-quality, large-scale, and standardized benchmark datasets for agricultural remote sensing.

• System Integration and Future Perspectives:
  
  • Integrated sky–ground cooperative systems for intelligent agricultural perception and decision-making.
  • Real-world implementation of "AI + remote sensing" solutions in smart farms, digital rural communities, and agricultural insurance platforms.
  • Critical discussion of technical, ethical, and operational challenges, along with strategic roadmaps for future development in the field.

• Research Articles: Original and comprehensive research papers that present novel scientific findings, methodological advancements, or empirical results with clear implications for the field.
• Review Articles: Systematic, critical, and up-to-date syntheses of current knowledge in specific research areas, including identification of key challenges, gaps, and future directions.

Dr. Yahui Guo
Dr. Meiyan Shu
Dr. Mario Cunha
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Remote Sensing is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2700 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• artificial intelligence
• precision agriculture
• satellite and UAV remote sensing
• data fusion
• crop monitoring
• yield prediction
• aboveground biomass estimation