Science AI Journal
Environmental Science · Research topic

Open research questions in Remote Sensing in Agriculture

75 unresolved questions extracted from the limitations and future-work sections of 750 Remote Sensing in Agriculture papers in our library. Each links back to the study that raised it.

What the literature leaves open

  • Satellite remote sensing has proven useful in studies of urban green spaces to evaluate vegetation health and conditions, but it has not yet been explored for long-term GR vegetation monitoring.

    Multi-temporal Green Roof Vegetation Assessment Using Sentinel-2: A Pilot Study · 2026 · DOI

  • (2) The correlations between vegetation indices and LNC varied markedly among different growth stages, suggesting that the spectral response of citrus LNC has strong phenological dependence and that a single vegetation index is insufficient to stably characterize LNC variation across the whole growth period.

    UAV Multispectral Estimation of Citrus Leaf Nitrogen Content by Integrating Object-Based Canopy Extraction and PSO-Optimized Machine Learning · 2026 · DOI

  • Accurate estimation of crop plant height using unmanned aircraft system (UAS) imagery combined with structure-from-motion (SfM) photogrammetry is critical for plant phenotyping and precision agriculture; however, few studies have systematically evaluated how camera type, spectral conguration, and ground sampling distance (GSD) inuence height estimation accuracy.

    Evaluating three cameras for cotton plant height estimation using UAS-derived point clouds · 2026 · DOI

  • Although self-supervised learning (SSL) offers a promising way to reduce annotation effort in close-range remote sensing, its effectiveness for high-resolution multispectral unmanned aerial vehicle (UAV) imagery remains underexplored due to limited data.

    Self-supervised training for high-resolution close-range multispectral remote sensing imagery · 2026

  • Mountain transition zones are highly sensitive to environmental change, yet the nonlinear coupling between topography and hydroclimate in controlling vegetation Net Primary Productivity (NPP) remains insufficiently constrained.

    Topographic–Climatic Interactions Drive Vegetation NPP Dynamics in the West Qinling Mountains (2003–2025) · 2026 · DOI

  • Nevertheless, several limitations of the present study warrant acknowledgment. A notable limitation of the present study pertains to the system's continued dependence on ground truth annotations, both in the determination of initial point placement and the application of the Negative Point Correction (NPC) method.

    Improving SAM 2 for Agricultural Land Segmentation through Fine-Tuning, Point Prompt Augmentation, and Negative Prompt Calibration · 2026 · DOI

  • However, future work should consider implementing spatial block cross- validation and, where feasible, external validation across independent forest regions to assess spatial transferability and generate more conservative, operational estimates for wall-to- integrating mechanistic wall mapping. Future work could explore these areas to enable attribution of uncertainty to specific components of the workflow.

    Explainable HybridEnsemble approach with golden jackal optimization for AGB estimation using multi-sensor remote sensing · 2026 · DOI

  • should be acknowledged. Although GEDI footprints provide high-precision structural measurements, their spatial density is relatively low and patchy, which may lead to an underrepresentation of spatial variability in highly heterogeneous landscapes (Qi et al. 2019). Regression models based on Sentinel-2 data also require robust calibration and validation using representative samples, while disturbances such as smoke, ash, and canopy damage can affect spectral reflectance and introduce uncertainty. Future studies could benefit from incorporating additional data sources, such as Sentinel-1 synthetic aperture radar (SAR), which is less sensitive to atmospheric conditions and provides valuable additional information on forest structure (Rüetschi et al. 2023). From an ecological perspective, the observed reduction in AGB in Luhansk Oblast has grave consequences, including weakening the protective functions of forests, reducing their carbon sequestration capacity, and increasing the risks of soil erosion and habitat destabilization. Forest degradation can also hinder post-conflict infrastructure recovery and increase pressures on local ecosystems during the reconstruction phase. Similar ecological consequences have been documented in other conflict-affected regions, underscoring the global relevance of the issues addressed in this study (Hanson et al. 2009; Reo et al. 2021). Overall, this study confirms the applicability and robustness of an integrated remote sensing approach based on GEDI and Sentinel-2 data for monitoring forest biomass losses caused by the war. The statistical robustness of the results is confirmed by high coefficients of determination, with R² values of 0.715 for the Kuzmyne site, 0.704 for Metolkine, and 0.720 for Bobrove exceed those obtained in recent studies such as Singha (2025), who achieved a maximum R² Folia Forestalia Polonica, Series A – Forestry, 2026, Vol. 68 (1), 33–45 of 0.71 when predicting forest AGB using SAR imagery and GEDI data combined with machine learning methods in a GEE environment. The regression slopes ranged from 0.597 to 0.73, indicating systematic underestimation of high AGB values and overestimation of low AGB values. This effect, commonly referred to as regression dilution or saturation bias, has been widely reported in optical remote sensing-based biomass estimation. Optical sensors such as Sentinel-2 are sensitive to canopy structure and vegetation indices but exhibit reduced sensitivity at high biomass levels due to signal saturation (Mutanga and Skidmore 2004). The ability to estimate biomass without field measurements is particularly valuable in disturbed or inaccessible regions.

    Decrease in forest above-ground biomass in war-damaged forests of Ukraine: A case study using GEDI, Sentinel-2 data, and the GEE platform · 2026 · DOI

  • Forest spatial structure is a key dimension of ecosystem change, yet its scale-dependent relationships with gross primary productivity (GPP) remain insufficiently understood at large spatial extents.

    Scale-dependent effects of forest spatial structure on gross primary productivity across China · 2026 · DOI

  • The effects of VRA/VRMA based on PC derived from colour UAV imagery require further investigation, particularly in grasslands and ruminant-based farming systems. The diminishing yield response to N at high supply levels suggests that applying lower maximum manure rates than those used in this study may help to reduce the masking effects of surplus N inputs. The influence of overwintering on remote-sensing-based N recommendations should be evaluated across multiple fields with varying winter severity. Such assessments are also needed to determine the feasibility of generating N application maps early in the season to support management planning. Multi-site experiments would further help to assess the consistency of the effects reported here across a broader range of soil types and botanical compositions representative of forage-grass systems in high-latitude regions. Furthermore, studies incorporating controlled irrigation could clarify how water availability interacts with VRMA. Considering these efforts together could support the development of integrated nutrient budgets (N, P, K) that improve manure management efficiency at both farm and regional scales, enabling higher application rates where nutrient demand is high whilst simultaneously reducing inputs in areas prone to nutrient surpluses.

    Optimising nitrogen application rate using grass coverage estimated at late autumn or early spring from RGB image analyses · 2026 · DOI

  • Use of SPAD meter in temperate deciduous forest research Few studies have used the SPAD handheld chlorophyll meter in forest research and none to our knowledge have used it to characterize autumn senescence patterns across multiple tem- perate deciduous shrub species.

    Native shrubs senesce earlier and faster than non-native shrubs in a temperate deciduous woodland in south-eastern Wisconsin, USA · 2026 · DOI

  • SPAD-derived provide detailed leaf-level information but do not capture spatial chlorophyll measurements heterogeneity across entire canopies or shrubs. As a result, observed senescence patterns may not directly translate to canopy-scale optical properties or ecosystem-level carbon dynamics. Therefore, it may be useful in future to increase the number of leaves, species and sites for which SPAD readings are taken. This would certainly capture a wider range of variability in terms of species and geography, and we encourage researchers to conduct more studies like this one. The optimum number of each would depend on the objectives of the study and the availability of resources. This analysis focused primarily on two air temperature metrics (average August temperature and autumn cooling thresholds) but this could be extended to explore a wider range of temperature parameters including average maximum and minimum temperatures, daytime and nighttime temperatures over different time period. In addition, other environmental factors known to influence autumn senescence—such as soil moisture, photoperiod interactions, drought stress, or extreme weather events (e.g., early frosts)—were not explic- itly quantified and may contribute to unexplained variability, and should be considered in future work.

    Native shrubs senesce earlier and faster than non-native shrubs in a temperate deciduous woodland in south-eastern Wisconsin, USA · 2026 · DOI

  • Summary Future research should focus on (a) expanding studies into underrepresented domains; (b) developing flexible yet standardised host-herbivory specific ground-truthing protocols; (c) refining methods to separate foliage types and confounding stressors; (d) advancing time-series analysis for monitoring outbreak dynamics; and (e) quantifying herbivory impacts on tree growth and forest productivity.

    Remote Sensing of Foliar Insect Herbivory in Broadleaved Forests: A Systematic Review · 2026 · DOI

  • The main goal in this work, how- ever, was not a certain amount of performance gain for the same task, but the development of a new method that allows for exploratory 3-D visual analyses via interactive and in situ visualization, and is sufficiently efficient and customized to facilitate novel approaches for addressing open questions in crop epidemiology regarding biological flows in the atmo- sphere.

    AgPaDS v1.0: a GPU-accelerated interactive Lagrangian atmospheric transport model with 3-D in situ visualization for simulating windborne dispersal of crop pathogens · 2026 · DOI

  • in sensitivity and accuracy because it depends on visual and conditions environmental during measurement. Additionally, variations in plant variety and other nutrient deficiencies may influence the results.

    Determination of the Vegetative Phase Critical for Monitoring Wheat Nitrogen Status Tropical Through Digital Color Analysis and Index Camera Reflectance · 2026 · DOI

  • Several limitations warrant acknowledgment. The first-order Markov assumption—that future shares depend only on current shares—ignores potential dependencies on rates of change or external drivers such as commodity prices, population growth, or climate.

    Forecasting US land use through 2067 using multi-method projections applied to seven decades of USDA data · 2026 · DOI

  • First, are governmental institutions should strengthen agricultural and meteorological data collection systems by improving monitoring infrastructure, expanding weather station networks, and standardizing agricultural reporting mechanisms across regions.

    BAYESIAN SPATIOTEMPORAL MODELING OF CLIMATE-INDUCED AGRICULTURAL YIELD VARIABILITY IN PAKISTAN UNDER DATA SCARCITY CONDITIONS · 2026 · DOI

  • Based on the findings of the study, several recommendations First, are governmental institutions should strengthen agricultural and meteorological data collection systems by improving monitoring infrastructure, expanding weather station networks, and standardizing agricultural reporting mechanisms across regions.

    BAYESIAN SPATIOTEMPORAL MODELING OF CLIMATE-INDUCED AGRICULTURAL YIELD VARIABILITY IN PAKISTAN UNDER DATA SCARCITY CONDITIONS · 2026 · DOI

  • The study demonstrates potential for integrating chlorophyll fluorescence with broader vegetation indices (e.g., NDVI) to enhance detection of phenological transitions and stress responses across diverse plant communities, but specific protocols for index combination and threshold determination in croplands, grasslands, and wetlands have not been established.

    Explainable machine learning for tracking spatial variation in leaf chlorophyll fluorescence within temperate deciduous forest canopies · 2026 · DOI

  • Persistent cloud cover limits optical remote sensing data acquisition for temporal monitoring of vegetation phenology and chlorophyll fluorescence dynamics, as demonstrated by Bartold and Kluczek (2024) regarding PSIImax estimation. Integration of synthetic aperture radar (SAR) with optical and LiDAR data through data fusion frameworks should be developed to mitigate weather-related observation gaps and enable consistent long-term ChlF monitoring.

    Explainable machine learning for tracking spatial variation in leaf chlorophyll fluorescence within temperate deciduous forest canopies · 2026 · DOI

  • Chlorophyll fluorescence signals are highly sensitive to short-term physiological changes and vulnerable to environmental noise, canopy structure effects, and sensor limitations, unlike indirect indices such as NDVI. Future research must explicitly develop uncertainty quantification methods and error propagation frameworks for chlorophyll fluorescence-based remote sensing to ensure robust and scalable ecological monitoring across varying environmental conditions.

    Explainable machine learning for tracking spatial variation in leaf chlorophyll fluorescence within temperate deciduous forest canopies · 2026 · DOI

  • Species-specific attributes and leaf position information were identified as critical predictors for spatial variation in chlorophyll fluorescence, but their collection via traditional survey methods is labor-intensive and geographically limited. The paper proposes integrating UAVs and ground-based LiDAR for automated quantification of species traits and canopy structure, but specific protocols for combining these remote sensing data with spectral reflectance for ChlF prediction remain undeveloped.

    Explainable machine learning for tracking spatial variation in leaf chlorophyll fluorescence within temperate deciduous forest canopies · 2026 · DOI

  • While SHAP was employed to improve interpretability, the mechanistic understanding of how spectral reflectance drives chlorophyll fluorescence predictions remains limited. Future work should integrate the Random Forest model with process-based models (e.g., radiative transfer models) following the framework of Wolanin et al. (2019) to bridge predictive accuracy with photosynthetic mechanism understanding.

    Explainable machine learning for tracking spatial variation in leaf chlorophyll fluorescence within temperate deciduous forest canopies · 2026 · DOI

  • The Random Forest and XGBoost models for predicting chlorophyll fluorescence parameters were trained exclusively on temperate deciduous forest datasets. These models require retraining and validation across diverse ecosystems (croplands, grasslands, wetlands) to assess transferability and determine whether spectral reflectance-ChlF relationships remain consistent across different plant functional types and canopy architectures.

    Explainable machine learning for tracking spatial variation in leaf chlorophyll fluorescence within temperate deciduous forest canopies · 2026 · DOI

  • The study achieved R² of 0.997 on internal validation but acknowledges these are preliminary findings under current experimental conditions; validation using longer time-series data spanning multiple growing seasons and high-resolution UAV LiDAR observations as benchmark references is necessary to establish external validity.

    A Sugarcane Height Estimation Model Based on Multi-Source Satellite Data Fusion Using Machine Learning · 2026 · DOI

Most-cited papers in Remote Sensing in Agriculture

Most recent work

Find a gap in your own Remote Sensing in Agriculture sub-topic

This page shows what the Remote Sensing in Agriculture literature already flags as unresolved. To narrow it to your specific question, run the guided finder — it searches the gap library on demand and checks candidates against 250M+ OpenAlex works.

Open the Research Gap Finder →

Related topics in Environmental Science

Environmental Education and Sustainability
249 open questions
Sustainability and Climate Change Governance
174 open questions
Microplastics and Plastic Pollution
146 open questions
Species Distribution and Climate Change
122 open questions
Wildlife Ecology and Conservation
117 open questions
Air Quality and Health Impacts
117 open questions
Climate variability and models
117 open questions
Urban Green Space and Health
107 open questions
75 open questions have been extracted from the limitations and future-work passages of 750 Remote Sensing in Agriculture papers in our library. Each one below links back to the study that raised it, so you can read the original claim in context.

Tools for your next paper

Gaps & Literature SearchFind open questions in any field — 120,000+ open gaps mined from our own library.Pre-CheckIs your paper ready? A Tier 1–5 acceptance probability in seconds.Journal FinderA ranked shortlist of target journals from a 17,500-venue index.Duplicate Publication CheckerCheck prior-publication & salami-slicing risk across 8 sources.Citation GeneratorFreeA DOI or title → APA, MLA, Vancouver, Chicago, BibTeX, RIS. No signup.Graphical Abstract MakerFreeTurn your findings into a colorblind-safe graphical abstract.

Compare the category — Honest roundups of the AI research tools, ours listed alongside the alternatives.

Command palette

Jump anywhere, run any action.