Forecasting vegetation indices from spatio-temporal remotely sensed data using deep learning-based approaches: A systematic literature review

Artificial intelligence for modeling and understanding extreme weather and climate events

In recent years, artificial intelligence (AI) has deeply impacted various fields, including Earth system sciences, by improving weather forecasting, model emulation, parameter estimation, and the prediction of extreme events. The latter comes with specific challenges, such as developing accurate predictors from noisy, heterogeneous, small sample sizes and data with limited annotations. This paper reviews how AI is being used to analyze extreme climate events (like floods, droughts, wildfires, and heatwaves), highlighting the importance of creating accurate, transparent, and reliable AI models. We discuss the hurdles of dealing with limited data, integrating real-time information, and deploying understandable models, all crucial steps for gaining stakeholder trust and meeting regulatory needs. We provide an overview of how AI can help identify and explain extreme events more effectively, improving disaster response and communication. We emphasize the need for collaboration across different fields to create AI solutions that are practical, understandable, and trustworthy to enhance disaster readiness and risk reduction.

Modeling Climate-Driven Vegetation Changes Under Contrasting Temperate and Arid Conditions in the Mediterranean Basin

This study investigates climate change impacts on spontaneous vegetation, focusing on the Mediterranean basin, a hotspot for climatic changes. Two case study areas, Monti Sibillini (central Italy, temperate) and Sidi Makhlouf (Southern Tunisia, arid), were selected for their contrasting climates and vegetation. Using WorldClim's CMCC-ESM2 climate model, future vegetation distribution was predicted for 2050 and 2080 under SSP 245 (optimistic) and 585 (pessimistic) scenarios. Two spectral indices, NDVI (temperate area) and SAVI (arid area), served as vegetation proxies, classified into three classes using K-means (NDVI: high = mainly associated with woodlands, medium = shrublands, continuous grasslands and crops, low = discontinuous grasslands, bare soil, and rocks; SAVI: high = mainly associated with woods, olive trees, and crops, medium = shrublands and sparse olive trees, low = bare soil and saline areas). Classes validated with ESA WorldCover 2020 data and sampled via 1390 presence-only points. A set of 33 environmental variables (topography, soil, and bioclimatic) was screened using Pearson correlation matrices, and predictive models were built using four algorithms: MaxEnt, Random Forest, XG Boost, and Neural Network. Results revealed increasing temperatures and declining precipitation in both regions, confirming Mediterranean climate trends. Vegetation changes varied by area: in the temperate area, woodlands and shrublands were stable, but discontinuous grasslands expanded. In the arid area, woodlands gained suitable habitat, while bare soil declined under the pessimistic SSP 585 scenario. Both areas showed an upward shift for shrublands and grasslands. The models indicated significant shifts in areal distribution and environmental conditions, affecting habitat suitability and ecosystem dynamics. MaxEnt emerged as the most reliable algorithm for small presence-only datasets, effectively predicting habitat suitability. The findings highlight significant vegetation redistribution and altered ecosystem dynamics due to climate change, underscoring the importance of these models in planning for future ecological challenges.

Analysis of the integrated role of the Yangtze River Delta based on the industrial economic resilience of cities during COVID-19

The enhancement of regional comprehensive development ability is significantly impacted by the study on the implementation effect of regional integration strategies. The integration strategy's impact on urban development during COVID-19 in the Yangtze River Delta(YRD) is unclear. According to prior industrial transfer theory, Hefei, Anhui's capital, is difficult to transfer industries, and other YRD cities push industry integration in Anhui. This study employs the theory of economic and land resource use to examine the resilience of the industrial economy during an epidemic by using industrial land as a representation of industrial economic development. The three cities in Anhui-Wuhu, Maanshan, and Chuzhou (Wu-ma-Chu) were selected as the research area. The study employed the UNet deep learning method to detect the land use types in Wu-ma-Chu. The land transfer matrix and the standard deviation ellipse were utilised to research the alterations in industrial land use and the spatial distribution of industrial output value, respectively. The results showed that the industrial land in Machu continued to grow during the outbreak, highlighting the resilience of the region's industrial economy. During 2019-2022, the elliptical ring of industrial output value is distributed in Nanjing, revealing the radiating role of Nanjing in integrating into the integration of the YRD. This confirms China's YRD integration strategy, strengthens regional economic resilience, and encourages coordinated regional economic development.

Next-level vegetation health index forecasting: A ConvLSTM study using MODIS Time Series

The Vegetation Health Index (VHI) is a metric used to assess the health and condition of vegetation, based on satellite-derived data. It offers a comprehensive indicator of stress or vigor, commonly used in agriculture, ecology, and environmental monitoring for forecasting changes in vegetation health. Despite its advantages, there are few studies on forecasting VHI as a future projection, particularly using up-to-date and effective machine learning methods. Hence, the primary objective of this study is to forecast VHI values by utilizing remotely sensed images. To achieve this objective, the study proposes employing a combined Convolutional Neural Network (CNN) and a specific type of Recurrent Neural Network (RNN) called Long Short-Term Memory (LSTM), known as ConvLSTM. The VHI time series images are calculated based on the Normalized Difference Vegetation Index (NDVI) and Land Surface Temperature (LST) data obtained from the Moderate Resolution Imaging Spectroradiometer (MODIS) aboard the Terra and Aqua satellites. In addition to the traditional image-based calculation, the study suggests using global minimum and global maximum values (global scale) of NDVI and LST time series for calculating the VHI. The results of the study showed that the ConvLSTM with a 1-layer structure generally provided better forecasts than 2-layer and 3-layer structures. The average Root Mean Square Error (RMSE) values for the 1-step, 2-step, and 3-step ahead VHI forecasts were 0.025, 0.026, and 0.026, respectively, with each step representing an 8-day forecast horizon. Moreover, the proposed global scale model using the applied ConvLSTM structures outperformed the traditional VHI calculation method.

Analysis of Dieback in a Coastal Pinewood in Campania, Southern Italy, through High-Resolution Remote Sensing

For some years, the stone pine (Pinus pinea L.) forests of the Domitian coast in Campania, Southern Italy, have been at risk of conservation due to biological adversities. Among these, the pine tortoise scale Toumeyella parvicornis (Cockerell) has assumed a primary role since its spread in Campania began. Observation of pine forests using remote sensing techniques was useful for acquiring information on the health state of the vegetation. In this way, it was possible to monitor the functioning of the forest ecosystem and identify the existence of critical states. To study the variation in spectral behavior and identify conditions of plant stress due to the action of pests, the analysis of the multispectral data of the Copernicus Sentinel-2 satellite, acquired over seven years between 2016 and 2022, was conducted on the Domitian pine forest. This method was used to plot the values of individual pixels over time by processing spectral indices using Geographic Information System (GIS) tools. The use of vegetation indices has made it possible to highlight the degradation suffered by the vegetation due to infestation by T. parvicornis. The results showed the utility of monitoring the state of the vegetation through high-resolution remote sensing to protect and preserve the pine forest ecosystem peculiar to the Domitian coast.

An Optimization Method of Deep Transfer Learning for Vegetation Segmentation under Rainy and Dry Season Differences in a Dry Thermal Valley

Deep learning networks might require re-training for different datasets, consuming significant manual labeling and training time. Transfer learning uses little new data and training time to enable pre-trained network segmentation in relevant scenarios (e.g., different vegetation images in rainy and dry seasons); however, existing transfer learning methods lack systematicity and controllability. So, an MTPI method (Maximum Transfer Potential Index method) was proposed to find the optimal conditions in data and feature quantity for transfer learning (MTPI conditions) in this study. The four pre-trained deep networks (Seg-Net (Semantic Segmentation Networks), FCN (Fully Convolutional Networks), Mobile net v2, and Res-Net 50 (Residual Network)) using the rainy season dataset showed that Res-Net 50 had the best accuracy with 93.58% and an WIoU (weight Intersection over Union) of 88.14%, most worthy to transfer training in vegetation segmentation. By obtaining each layer's TPI performance (Transfer Potential Index) of the pre-trained Res-Net 50, the MTPI method results show that the 1000-TDS and 37-TP were estimated as the best training speed with the smallest dataset and a small error risk. The MTPI transfer learning results show 91.56% accuracy and 84.86% WIoU with 90% new dataset reduction and 90% iteration reduction, which is informative for deep networks in segmentation tasks between complex vegetation scenes.

UAV Remote Sensing for High-Throughput Phenotyping and for Yield Prediction of Miscanthus by Machine Learning Techniques

Miscanthus holds a great potential in the frame of the bioeconomy, and yield prediction can help improve Miscanthus’ logistic supply chain. Breeding programs in several countries are attempting to produce high-yielding Miscanthus hybrids better adapted to different climates and end-uses. Multispectral images acquired from unmanned aerial vehicles (UAVs) in Italy and in the UK in 2021 and 2022 were used to investigate the feasibility of high-throughput phenotyping (HTP) of novel Miscanthus hybrids for yield prediction and crop traits estimation. An intercalibration procedure was performed using simulated data from the PROSAIL model to link vegetation indices (VIs) derived from two different multispectral sensors. The random forest algorithm estimated with good accuracy yield traits (light interception, plant height, green leaf biomass, and standing biomass) using 15 VIs time series, and predicted yield using peak descriptors derived from these VIs time series with root mean square error of 2.3 Mg DM ha−1. The study demonstrates the potential of UAVs’ multispectral images in HTP applications and in yield prediction, providing important information needed to increase sustainable biomass production.

LSTM-Based Prediction of Mediterranean Vegetation Dynamics Using NDVI Time-Series Data

Vegetation index time-series analysis of multitemporal satellite data is widely used to study vegetation dynamics in the present climate change era. This paper proposes a systematic methodology to predict the Normalized Difference Vegetation Index (NDVI) using time-series data extracted from the Moderate Resolution Imaging Spectroradiometer (MODIS). The key idea is to obtain accurate NDVI predictions by combining the merits of two effective computational intelligence techniques; namely, fuzzy clustering and long short-term memory (LSTM) neural networks under the framework of dynamic time warping (DTW) similarity measure. The study area is the Lesvos Island, located in the Aegean Sea, Greece, which is an insular environment in the Mediterranean coastal region. The algorithmic steps and the main contributions of the current work are described as follows. (1) A data reduction mechanism was applied to obtain a set of representative time series. (2) Since DTW is a similarity measure and not a distance, a multidimensional scaling approach was applied to transform the representative time series into points in a low-dimensional space, thus enabling the use of the Euclidean distance. (3) An efficient optimal fuzzy clustering scheme was implemented to obtain the optimal number of clusters that better described the underline distribution of the low-dimensional points. (4) The center of each cluster was mapped into time series, which were the mean of all representative time series that corresponded to the points belonging to that cluster. (5) Finally, the time series obtained in the last step were further processed in terms of LSTM neural networks. In particular, development and evaluation of the LSTM models was carried out considering a one-year period, i.e., 12 monthly time steps. The results indicate that the method identified unique time-series patterns of NDVI among different CORINE land-use/land-cover (LULC) types. The LSTM networks predicted the NDVI with root mean squared error (RMSE) ranging from 0.017 to 0.079. For the validation year of 2020, the difference between forecasted and actual NDVI was less than 0.1 in most of the study area. This study indicates that the synergy of the optimal fuzzy clustering based on DTW similarity of NDVI time-series data and the use of LSTM networks with clustered data can provide useful results for monitoring vegetation dynamics in fragmented Mediterranean ecosystems.