It is argued that future progress depends less on incremental accuracy gains than on reproducible multi-source workflows, explicit uncertainty, trustworthy and explainable geospatial artificial intelligence, privacy-preserving governance, interoperable standards and evaluation in the institutions that ultimately use the evidence.
Abstract
Geospatial technology has evolved from a set of specialised mapping tools into an integrated decision infrastructure that links Earth observation, geographic information systems, satellite positioning, uncrewed aerial systems, volunteered geographic information, cloud computing and geospatial artificial intelligence. This critical narrative review examines how that integration is changing evidence production and decision support across agriculture, environmental and biodiversity monitoring, disaster risk management, urban and transport planning, and public health. Literature published primarily from 2000 to 9 June 2026 was selected through live web-based scholarly discovery, DOI and bibliographic verification, citation chaining and targeted searches of accessible scholarly records. The evidence indicates that geospatial systems are most valuable when they combine complementary observations across scales rather than relying on a single sensor, platform or algorithm. Their strongest contributions are spatially explicit monitoring, prioritisation, scenario analysis and repeated observation, while the weakest parts of many workflows remain ground-reference quality, uncertainty propagation, transferability, interoperability and evaluation against operational outcomes. Cloud platforms and deep learning have expanded computational reach, but they can also conceal provenance, amplify geographic bias and encourage benchmark-driven optimisation that does not translate reliably across places. Volunteered data and urban digital twins extend participation and real-time representation, yet introduce uneven coverage, privacy, governance and accountability concerns. The review argues that future progress depends less on incremental accuracy gains than on reproducible multi-source workflows, explicit uncertainty, trustworthy and explainable geospatial artificial intelligence, privacy-preserving governance, interoperable standards and evaluation in the institutions that ultimately use the evidence. Geospatial technology should therefore be judged not only by spatial resolution or predictive performance, but by whether it produces defensible, equitable and actionable knowledge across heterogeneous real-world settings.
Monitoring of the atmosphere is experiencing a paradigm shift due to a combination of big data, electronic information technologies, and geographic information systems (GIS). Conventional methods of monitoring, which are largely based on sparse fixed-site stations, usually experience spatial constraints, limited time responsiveness, and challenges in integrating multiple sources. This paper provides a systematic review of how the joint evolution of dense sensing networks, real-time communication systems, big-data analytics, and geospatial platforms is transforming existing atmospheric observation systems into smarter and decision-oriented structures. The paper first presents the technological background of integrated atmospheric monitoring, such as heterogeneous data sources, sensor and communication infrastructure, and GIS-based spatial intelligence. It then examines key processes of data preprocessing and quality control, multi-source fusion, spatiotemporal modeling, visualization, and uncertainty-conscious interpretation. Significant application areas are also examined, among which are urban air quality control, regional pollution monitoring, emergency response, and public health assessment. The current limitations are also critically assessed in the review (including data heterogeneity, unstable calibration, scale and location issues, interoperability, propagation of uncertainties, and poor model interpretability). Based on this assessment, future trends are determined to include explainable artificial intelligence, edge intelligence, digital twin platforms, and more standardized and resilient monitoring architectures. The originality of this review is its integrated approach, which does not consider big data, electronic information, and GIS as independent technical solutions, but rather views them as complementary components and pillars of next-generation atmospheric monitoring. The review serves as a systematic source for the development of more accurate, adaptive, and governance-oriented atmospheric monitoring systems.
Remote sensing (RS) and geographic information systems (GIS) increasingly support ecosystem and biodiversity monitoring, yet evidence remains fragmented across sensors, indicators, analytical methods, and policy applications. This review synthesises 163 peer-reviewed studies published from 2015 to 2025 to determine how RS and GIS indicators can be selected, validated, and translated into decision-relevant evidence. The synthesis compares satellite and unmanned aerial vehicle platforms, vegetation indices, change-detection techniques, landscape metrics, machine-learning models, cloud-computing workflows, and multi-scale validation strategies. No sensor, index, or classifier is universally optimal. Landsat and Sentinel-2 provide the strongest basis for long-term and large-area monitoring, whereas commercial imagery and unmanned aerial vehicles better resolve fine habitat features and localised disturbance. Vegetation indices remain useful ecosystem proxies but cannot independently represent species composition, ecological integrity, or causal degradation processes. Reliable applications therefore require context-specific indicator selection, transparent preprocessing, representative ground reference data, uncertainty reporting, and integration of spectral, structural, ecological, and socio-economic evidence. Data fusion and machine learning improve monitoring performance when validation is rigorous, but computational sophistication cannot compensate for weak reference data. The review concludes that policy value depends on converting remotely sensed change into explicit, validated decision rules for zoning, restoration, protected-area management, and biodiversity reporting.
T. Mkilima, A. Zhidebayeva, S. Syrlybekkyzy et al.· Environmental Engineering Re...· 0 citations
Abstract. The field of geospatial artificial intelligence (GeoAI) has brought transformative opportunities to the geospatial domain. Technological advances in machine learning and deep learning, the proliferation of big geospatial data of different sources, computing power capabilities, and the expansion of geographic information systems (GIS) have all contributed to the impact of GeoAI technological trends. National mapping agencies (NMAs) represent a promising and ongoing area for the implementation of GeoAI, enabling them to fully leverage its advantages given the nationwide data infrastructures managed, the missions accomplished, and the challenges faced. However, the implementation of the GeoAI solution also involves technical and ethical constraints that must be taken into account. This paper reviews the integration of GeoAI within NMAs, focusing on practical applications, technical challenges, and ethical considerations. Based on recent scientific literature and institutional reports, the study defines four main application domains: geospatial data extraction, change detection, 3D point cloud classification and standardization of geographical names. The study present how NMAs are leveraging GeoAI to improve efficiency, data quality, and the automation of mapping workflows, while addressing challenges related to data availability, AI infrastructure, and human expertise. The article also discusses key aspects of trustworthy GeoAI, such as explainability, bias and geoprivacy. By bridging applied scientific research and the practical applications, this paper provides a structured overview of a transformative emerging technology, GeoAI, within the context of organizations as specific as NMAs and presents the future trends, such as the development of geofoundational models and agentic AI.
Zineb Didouz, I. Sebari, Kenza Ait El Kadi· The International Archives o...· 0 citations
Earth Observation (EO) analysis increasingly relies on large and heterogeneous satellite datasets, yet developing EO workflows often requires specialized expertise in data selection, geospatial programming, and cloud-based processing. Recent advances in Large Language Models (LLMs) offer new opportunities for natural-language interaction with EO systems, although challenges related to transparency, reproducibility, and domain-specific reasoning remain. This study presents SeaScope, an explainable AI framework that integrates LLMs, Retrieval-Augmented Generation (RAG), scientific knowledge retrieval, and Google Earth Engine (GEE) to transform natural-language requests into transparent and executable EO workflows. The framework combines knowledge retrieval, code generation, cloud execution, provenance tracking, and interactive visualization within a unified environment. A pilot implementation is demonstrated through maritime and coastal monitoring applications, including oil spill detection, vessel monitoring, water quality assessment, floating debris detection, and air quality analysis. Multiple state-of-the-art LLMs are evaluated under both RAG and non-RAG configurations using representative EO case studies. The results indicate substantial differences among model families and show that retrieval augmentation can significantly improve workflow generation quality and reliability for capable models, while providing more limited benefits for smaller models. The proposed framework demonstrates the potential of explainable AI agents to support transparent, reproducible, and scalable EO analysis.
