Machine learning (also called data-driven) methods have become popular in modeling flood inundations across river basins. Among data-driven methods, traditional machine learning (ML) approaches are widely used to model flood events, and recently deep learning (DL) approaches have gained more attention across the world. In this paper, we reviewed recently published literature on ML and DL applications for flood modeling for various hydrologic and catchment characteristics. Our extensive literature review shows that DL models produce better accuracy compared to traditional approaches. Unlike physically based models, ML/DL models suffer from the lack of using expert knowledge in modeling flood events. Apart from challenges in implementing a uniform modeling approach across river basins, the lack of benchmark data to evaluate model performance is a limiting factor for developing efficient ML/DL models for flood inundation modeling.

Understanding the historical and future spatio-temporal changes in climate extremes and their potential risk to rice production is crucial for achieving food security in Bangladesh. This paper presents results from a study on trend analysis for 13 climate metrics that significantly influence rice production. The analysis was conducted using the non-parametric Mann-Kendall test and the Theil-Sen slope estimator methods. The study included data from all available weather stations in Bangladesh and the assessment was done for both the wet (May to October) and dry (November to April) seasons, which cover the growing seasons of the country’s three types of rice: Aus, Aman and Boro. Results show significant decreasing trends for wet season rainfall (>12 mm/season/year in some stations) in the central and north regions. In addition, dry season rainfall is decreasing significantly in many areas, whilst dry season dry spells are increasing throughout Bangladesh. Decrease in rainfall in some of these areas are of concern because of its impacts on rainfed Aus rice and in the sowing/planting of rainfed Aman rice and irrigated dry season Boro rice. The maximum temperatures in the wet season are increasing throughout the country at 0.5°C every ten years, significantly at most of the climate stations. The analysis shows that the number of days with temperature >36°C has significantly increased in 18 stations over the last three decades, which implies a serious risk to Aman rice yield. The current maximum temperatures (both in the wet and dry seasons) are higher than the optimum temperature ranges for rice production, and this will have likely adverse effects on yield in the face of climate change with increasing temperatures. The results herein have practical implications for planning appropriate adaptation policies to ensure food security in the country.

The shallow tidal and freshwater coastal wetlands adjacent to the Great Barrier Reef lagoon provide a vital nursery and feeding complex that supports the life cycles of marine and freshwater fish, important native vegetation and vital bird habitat. Urban and agricultural development threaten these wetlands, with many of the coastal wetlands becoming lost or changed due to the construction of artificial barriers (e.g. bunds, roads, culverts and floodgates). Infestation by weeds has become a major issue within many of the wetlands modified (bunded) for ponded pasture growth last century. A range of expensive chemical and mechanical control methods have been used in an attempt to restore some of these coastal wetlands, with limited success. This study describes an alternative approach to those methods, investigating the impact of tidal reinstatement after bund removal on weed infestation, associated changes in water quality, and fish biodiversity, in the Boolgooroo lagoon region of the Mungalla wetlands, East of Ingham in North Queensland. High resolution remote sensing, electrofishing and in-water logging was used to track changes over time– 1 year before and 4 years after removal of an earth bund. With tides only penetrating the wetland a few times yearly, gross changes towards a more natural system occurred within a relatively short timeframe, leading to a major reduction in infestation of olive hymenachne, water hyacinth and salvina, reappearance of native vegetation, improvements in water quality, and a tripling of fish diversity. Weed abundance and water quality does appear to oscillate however, dependent on summer rainfall, as changes in hydraulic pressure stops or allows tidal ingress (fresh/saline cycling). With an estimated 30% of coastal wetlands bunded in the Great Barrier Reef region, a passive remediation method such as reintroduction of tidal flow by removal of an earth bund or levee could provide a more cost effective and sustainable means of controlling freshwater weeds and improving coastal water quality into the future.

Current estimates of sediment and nutrient loads from the Tully–Murray floodplain to the Great Barrier Reef lagoon are updated by taking explicit account of flood events. New estimates of flood discharge that include over-bank flows are combined with direct measurements of sediment and nutrient concentrations in flood waters to calculate the loads of sediment and nutrient delivered to the ocean during 13 floods that occurred between 2006 and 2008. Although absolute concentrations of sediment and nutrient were quite low, the large volume of water discharged during floods means that they make a large contribution (30–50%) to the marine load. By not accounting for flood flows correctly, previous estimates of the annual average discharge are 15% too low and annual loads of nitrogen and phosphorus are 47% and 32% too low respectively. However, because sediments may be source-limited, accounting for flood flows simply dilutes their concentration and the resulting annual average load is similar to that previously estimated. Flood waters also carry more dissolved organic nitrogen than dissolved inorganic nitrogen and this is the opposite of their concentrations in river water. Consequently, dissolved organic nitrogen loads to the ocean may be around twice those previously estimated from riverine data.